Further Statistical Methods, HT06

Overview of Lectures

The preliminary content of each of the lectures is as follows:

1. Introduction to categorical data and conditional independence
2. Log-linear and graphical models
3. Ordinal data and models for square tables
4. Missing data
5. The EM algorithm
6. Latent variable models
7. Factor analysis
8. Multi-level analysis
9. Longitudinal data
10. Alternative approaches to longitudinal data.

The material in the first 3 lectures is largely contained in books by Edwards and Agresti, see synopses for details on books. For most examples I am using the David Edwards' software MIM, which can be downloaded from here. For the MIM manual, see Edwards (2002), appendix A and B.

For lectures 4 and 5, see R. J. A. Little and D. B. Rubin (2002). Statistical Analysis with Missing Data, 2nd ed. Wiley, New York.

For lectures 6 and 7, see D. J. Bartholomew and M. Knott (1999). Latent Variable Models and Factor Analysis. Arnold, London

For lecture 8, see T. A. B. Snijders and R. J. Bosker (1999). Multi-level analysis. Sage Publications, London.

For lectures 9 and  10, see P. J. Diggle, P. Heagerty, K.-Y. Liang and S. L. Zeger (2002). Analysis of longitudinal data. Oxford University Press, Oxford.

Course page

Last updated: Wednesday, 22 February 2006 10:50.  Steffen L. Lauritzen