The lecture describes how genetic pedigree problems can be naturally cast in a Bayesian network setting. The lecture is based on the recent paper
S. L. Lauritzen and N. A. Sheehan. Graphical models for genetic analyses. Research Report R-02-2020. Department of Mathematical Sciences, Aalborg University, 2002. To appear in Statistical Science. .ps-version.
Directly relevant sections are 1, 2.1, 2.2, 2.4, 4. Section 3 has almost a full derivation and description of the local computation procedure. It was my aim to make it the best exposition existing, so it might be helpful for you to read this.
Overheads for screen-viewing and printing.