An Introduction to Graphical Models

Add to your list(s) Download to your calendar using vCal

• Robin Evans, Statistical Laboratory
• Wednesday 30 November 2011, 16:30-17:30
• MR4, CMS.

If you have a question about this talk, please contact Richard Samworth.

This talk has been canceled/deleted

Conditional independence is perhaps the most intuitive form of modelling structure or assumption, its essence being easily described to people without mathematical training. Graphical models provide a visual way of encoding (in)dependences amongst a collection of random variables, and perhaps their greatest feature is their simplicity. The ability to see these relationships has a great deal of practical relevance, particularly for communicating the structure of multivariate distributions to non-statisticians.

Even for the seasoned statistician, graphical models can provide new insights into common problems, such as understanding what to control for in an observational study, how our prior beliefs can be updated with new information, and approaches to the ideas of cause and effect.

In this talk we discuss undirected graphs, directed acyclic graphs (DAGs), and (if there is time) chain graphs, and graphs with bidirected edges.

This talk is part of the Statistics Reading Group series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.