* using log directory ‘/data/localhost/ripley/R/packages/tests-MKL/whatifbandit.Rcheck’
* using R Under development (unstable) (2026-10-30 r90795)
* using platform: x86_64-pc-linux-gnu
* R was compiled by
    gcc (GCC) 16.2.1 20260819 (Red Hat 16.2.1-2)
    GNU Fortran (GCC) 16.2.1 20260819 (Red Hat 16.2.1-2)
* running under: Fedora Linux 44 (Server Edition)
* using session charset: UTF-8
* current time: 2026-10-30 13:07:41 UTC
* using option ‘--no-stop-on-test-error’
* checking for file ‘whatifbandit/DESCRIPTION’ ... OK
* this is package ‘whatifbandit’ version ‘1.0.3’
* package encoding: UTF-8
* checking package namespace information ... OK
* checking package dependencies ... OK
* checking if this is a source package ... OK
* checking if there is a namespace ... OK
* checking for executable files ... OK
* checking for hidden files and directories ... OK
* checking for portable file names ... OK
* checking for sufficient/correct file permissions ... OK
* checking whether package ‘whatifbandit’ can be installed ... OK
* checking package directory ... OK
* checking ‘build’ directory ... OK
* checking DESCRIPTION meta-information ... OK
* checking top-level files ... OK
* checking for left-over files ... OK
* checking index information ... OK
* checking package subdirectories ... OK
* checking code files for non-ASCII characters ... OK
* checking R files for syntax errors ... OK
* checking whether the package can be loaded ... OK
* checking whether the package can be loaded with stated dependencies ... OK
* checking whether the package can be unloaded cleanly ... OK
* checking whether the namespace can be loaded with stated dependencies ... OK
* checking whether the namespace can be unloaded cleanly ... OK
* checking loading without being on the library search path ... OK
* checking use of S3 registration ... OK
* checking dependencies in R code ... OK
* checking S3 generic/method consistency ... OK
* checking replacement functions ... OK
* checking foreign function calls ... OK
* checking R code for possible problems ... OK
* checking Rd files ... OK
* checking Rd metadata ... OK
* checking Rd line widths ... OK
* checking Rd cross-references ... OK
* checking for missing documentation entries ... OK
* checking for code/documentation mismatches ... OK
* checking Rd \usage sections ... OK
* checking Rd contents ... OK
* checking for unstated dependencies in examples ... OK
* checking contents of ‘data’ directory ... OK
* checking data for non-ASCII characters ... OK
* checking LazyData ... OK
* checking data for ASCII and uncompressed saves ... OK
* checking installed files from ‘inst/doc’ ... OK
* checking files in ‘vignettes’ ... OK
* checking examples ... OK
* checking for unstated dependencies in ‘tests’ ... OK
* checking tests ...
  Running ‘testthat.R’ [288s/233s]
 [288s/233s] ERROR
Running the tests in ‘tests/testthat.R’ failed.
Complete output:
  > # This file is part of the standard setup for testthat.
  > # It is recommended that you do not modify it.
  > #
  > # Where should you do additional test configuration?
  > # Learn more about the roles of various files in:
  > # * https://r-pkgs.org/testing-design.html#sec-tests-files-overview
  > # * https://testthat.r-lib.org/articles/special-files.html
  > 
  > library(testthat)
  > library(whatifbandit)
  > 
  > test_check("whatifbandit")
  Starting 2 test processes.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont4: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont4: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_simulate.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_simulate.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t st
  > test-mab_simulate.r: atistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_simulate.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_simulate.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numer
  > test-mab_simulate.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numer
  > test-mab_simulate.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happ
  > test-mab_simulate.r: ens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont4: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numer
  > test-mab_simulate.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numer
  > test-mab_simulate.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numericall
  > test-mab_simulate.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numericall
  > test-mab_simulate.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients 
  > test-mab_simulate.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients 
  > test-mab_simulate.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are no
  > test-mab_simulate.r: t zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number
  > test-mab_simulate.r:  it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_simulate.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_simulate.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coeffici
  > test-mab_simulate.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numericall
  > test-mab_simulate.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numericall
  > test-mab_simulate.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_simulate.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_simulate.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numer
  > test-mab_simulate.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happ
  > test-mab_simulate.r: ens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numer
  > test-mab_simulate.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the clus
  > test-mab_simulate.r: ter-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont1: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2: the cluster-level scores for that coefficient sum to numerically zero, so the clus
  > test-mab_simulate.r: ter-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_simulate.r: The standard error is NA for mab_conditiont2: the cluster-level scores for that coefficient sum to numerically zero, so the clus
  > test-mab_simulate.r: ter-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  Saving _problems/test-mab_simulate-98.R
  Saving _problems/test-mab_simulate-98.R
  Saving _problems/test-mab_simulate-98.R
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t st
  > test-mab_from_rct.r: atistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: every observation that identifies that coefficient is fitted exactly, so the varia
  > test-mab_from_rct.r: nce is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2: every observation that identifies that coefficient is fitted exactly, so the variance is built from residuals that are all numerically zero. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3: the cluster-level scores for those coefficients sum to numer
  > test-mab_from_rct.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients 
  > test-mab_from_rct.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients 
  > test-mab_from_rct.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the clust
  > test-mab_from_rct.r: er-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, althou
  > test-mab_from_rct.r: gh the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals 
  > test-mab_from_rct.r: themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens w
  > test-mab_from_rct.r: hen a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals 
  > test-mab_from_rct.r: themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont5: the cluster-level scores for those coeffici
  > test-mab_from_rct.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients 
  > test-mab_from_rct.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients 
  > test-mab_from_rct.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the clust
  > test-mab_from_rct.r: er-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the clust
  > test-mab_from_rct.r: er-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, althou
  > test-mab_from_rct.r: gh the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the clust
  > test-mab_from_rct.r: er-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the clust
  > test-mab_from_rct.r: er-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coeffici
  > test-mab_from_rct.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are no
  > test-mab_from_rct.r: t zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number
  > test-mab_from_rct.r:  it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coeffici
  > test-mab_from_rct.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coeffici
  > test-mab_from_rct.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont3: the cluster-level scores for those coeffici
  > test-mab_from_rct.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont5: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont4: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont5: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores f
  > test-mab_from_rct.r: or those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients 
  > test-mab_from_rct.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients 
  > test-mab_from_rct.r: sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont2, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coeffici
  > test-mab_from_rct.r: ents sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont4, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont2, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the clus
  > test-mab_from_rct.r: ter-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is 
  > test-mab_from_rct.r: constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the clus
  > test-mab_from_rct.r: ter-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is 
  > test-mab_from_rct.r: constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont3: the cluster-level scores for that coefficient sum to numerically zero, so the clus
  > test-mab_from_rct.r: ter-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont2, mab_conditiont4: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens w
  > test-mab_from_rct.r: hen a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or r
  > test-mab_from_rct.r: ounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont3, mab_conditiont5: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol: the cluster-level scores for that coefficient sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numer
  > test-mab_from_rct.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3: the cluster-level scores for those coefficients sum to numericall
  > test-mab_from_rct.r: y zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditiont1, mab_conditiont3: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont1: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numer
  > test-mab_from_rct.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numer
  > test-mab_from_rct.r: ically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  > test-mab_from_rct.r: The standard error is NA for mab_conditioncontrol, mab_conditiont5: the cluster-level scores for those coefficients sum to numerically zero, so the cluster-robust variance is assembled from nothing, although the residuals themselves are not zero. That happens when a regressor is constant within cluster and the residuals cancel over the cluster. Reported as a number it would be zero or rounding error, and its t statistic would put p at 0.
  Saving _problems/test-mab_from_rct-114.R
  Saving _problems/test-mab_from_rct-114.R
  Saving _problems/test-mab_from_rct-114.R
  [ FAIL 6 | WARN 432 | SKIP 1 | PASS 1879 ]
  
  ══ Skipped tests (1) ═══════════════════════════════════════════════════════════
  • On CRAN (1): 'test-error_checking.r:7:1'
  
  ══ Failed tests ════════════════════════════════════════════════════════════════
  ── Error ('test-mab_simulate.r:98:9'): simulate_mab: space-filling argument and design coverage / simulate_mab: clustering contrasts ──
  <purrr_error_indexed/rlang_error/error/condition>
  Error in `map(.x, .f, ..., .progress = .progress)`: i In index: 4.
  Caused by error:
  ! Expected `new_df` to equal `df[[item]]`.
  Differences:
       actual[[5]] | expected[[5]]     
  [25] 1.000000000 | 1.000000000   [25]
  [26] 1.000000000 | 1.000000000   [26]
  [27] 1.999998684 | 1.999998684   [27]
  [28] 1.929543738 - 1.887992121   [28]
  [29] 1.000000000 | 1.000000000   [29]
  [30] 1.000000000 | 1.000000000   [30]
  [31] 2.000000000 | 2.000000000   [31]
  ── Error ('test-mab_simulate.r:98:9'): simulate_mab: space-filling argument and design coverage / simulate_mab: clustering mixed1 ──
  <purrr_error_indexed/rlang_error/error/condition>
  Error in `map(.x, .f, ..., .progress = .progress)`: i In index: 4.
  Caused by error:
  ! Expected `new_df` to equal `df[[item]]`.
  Differences:
       actual[[5]] | expected[[5]]     
  [14] 1.984166104 | 1.984166104   [14]
  [15] 1.000000000 | 1.000000000   [15]
  [16] 1.000000000 | 1.000000000   [16]
  [17] 1.958513554 - 1.988635024   [17]
  [18] 1.000000000 | 1.000000000   [18]
  [19] 1.000000000 | 1.000000000   [19]
  [20] 2.000000000 | 2.000000000   [20]
  
       actual[[5]] | expected[[5]]     
  [23] 2.000000000 | 2.000000000   [23]
  [24] 1.000000000 | 1.000000000   [24]
  [25] 1.000000000 | 1.000000000   [25]
  [26] 2.000000000 - 1.893407009   [26]
  [27] 1.000000000 | 1.000000000   [27]
  ── Error ('test-mab_simulate.r:98:9'): simulate_mab: space-filling argument and design coverage / simulate_mab: clustering mixed5 ──
  <purrr_error_indexed/rlang_error/error/condition>
  Error in `map(.x, .f, ..., .progress = .progress)`: i In index: 4.
  Caused by error:
  ! Expected `new_df` to equal `df[[item]]`.
  Differences:
       actual[[5]] | expected[[5]]     
  [11] 1.000000000 | 1.000000000   [11]
  [12] 1.000000000 | 1.000000000   [12]
  [13] 1.000000000 | 1.000000000   [13]
  [14] 2.000000000 - 1.893407009   [14]
  [15] 1.000000000 | 1.000000000   [15]
  ── Error ('test-mab_from_rct.r:114:9'): mab_from_rct: space-filling argument and design coverage / mab_from_rct: clustering random_assign ──
  <purrr_error_indexed/rlang_error/error/condition>
  Error in `map(.x, .f, ..., .progress = .progress)`: i In index: 4.
  Caused by error:
  ! Expected `new_df` to equal `df[[item]]`.
  Differences:
       actual[[5]] | expected[[5]]               
  [13] 9.000000000 | 9.000000000   [13]          
  [14] 9.000000000 | 9.000000000   [14]          
  [15] 9.000000000 | 9.000000000   [15]          
  [16] 1.871446295 - 1.703176785   [16]          
  [17] 1.978972097 - 1.989488786   [17]          
  [18] 2.774285137 | 2.774285137   [18]          
  [19] 1.000000000 | 1.000000000   [19]          
  [20] 1.990334041 - 1.977752064   [20]          
  [21] 1.775524695 | 1.775524695   [21]          
  [22] 2.774285137 | 2.774285137   [22]          
   ... ...           ...           and 1 more ...
  ── Error ('test-mab_from_rct.r:114:9'): mab_from_rct: space-filling argument and design coverage / mab_from_rct: clustering control ──
  <purrr_error_indexed/rlang_error/error/condition>
  Error in `map(.x, .f, ..., .progress = .progress)`: i In index: 4.
  Caused by error:
  ! Expected `new_df` to equal `df[[item]]`.
  Differences:
       actual[[5]] | expected[[5]]     
   [7] 9.000000000 | 9.000000000   [7] 
   [8] 9.000000000 | 9.000000000   [8] 
   [9] 9.000000000 | 9.000000000   [9] 
  [10] 1.974586868 - 1.996494814   [10]
  [11] 1.598623412 | 1.598623412   [11]
  [12] 1.000000000 | 1.000000000   [12]
  [13] 1.000000000 | 1.000000000   [13]
  
       actual[[5]] | expected[[5]]     
  [20] 2.000000000 | 2.000000000   [20]
  [21] 1.000000000 | 1.000000000   [21]
  [22] 1.000000000 | 1.000000000   [22]
  [23] 2.000000000 - 1.999485658   [23]
  [24] 1.000000000 | 1.000000000   [24]
  [25] 2.272727273 | 2.272727273   [25]
  [26] 2.000000000 | 2.000000000   [26]
  ── Error ('test-mab_from_rct.r:114:9'): mab_from_rct: space-filling argument and design coverage / mab_from_rct: clustering mixed1 ──
  <purrr_error_indexed/rlang_error/error/condition>
  Error in `map(.x, .f, ..., .progress = .progress)`: i In index: 4.
  Caused by error:
  ! Expected `new_df` to equal `df[[item]]`.
  Differences:
       actual[[5]] | expected[[5]]               
   [3] 9.000000000 | 9.000000000   [3]           
   [4] 9.000000000 | 9.000000000   [4]           
   [5] 9.000000000 | 9.000000000   [5]           
   [6] 1.631267959 - 1.822250690   [6]           
   [7] 1.000000000 | 1.000000000   [7]           
   [8] 1.000000000 | 1.000000000   [8]           
   [9] 1.000000000 | 1.000000000   [9]           
  [10] 1.000000000 | 1.000000000   [10]          
  [11] 2.000000000 - 1.999485658   [11]          
  [12] 1.000000000 | 1.000000000   [12]          
   ... ...           ...           and 2 more ...
  
  [ FAIL 6 | WARN 432 | SKIP 1 | PASS 1879 ]
  Error:
  ! Test failures.
  Execution halted
* checking for unstated dependencies in vignettes ... OK
* checking package vignettes ... OK
* checking re-building of vignette outputs ... [42s/43s] OK
* checking PDF version of manual ... OK
* checking HTML version of manual ... OK
* checking for non-standard things in the check directory ... OK
* checking for detritus in the temp directory ... OK
* DONE

Status: 1 ERROR
See
  ‘/data/localhost/ripley/R/packages/tests-MKL/whatifbandit.Rcheck/00check.log’
for details.

Command exited with non-zero status 1
Time 5:30.40, 368.23 + 9.74