If you’re in D.C., you should stop by. . . . I’m speaking in the statistics department at George Washington University on the topic of interactions. Here’s the powerpoint and here’s the abstract:

As statisticians and practitioners, we all know about interactions but we tend to think of them as an afterthought. We argue here that interactions are fundamental to statistical models. We first consider treatment interactions in before-after studies, then more general interactions in regressions and multilevel models. Using several examples from our own applied research, we demonstrate the effectiveness of routinely including interactions in regression models. We also discuss some of the challenges and open problems involved in setting up models for interactions.

The talk will be today, Wed 10 Sept, at 3pm at 1957 E Street, Room 212. If you don’t know where that is, you can call the department (202-994-6356) and they should be able to give you directions.

Tomorrow (Thurs) I’ll be speaking with Boris at noon at the Cato Institute on Red State, Blue State. It’s not too late to sign up for that.

Have you seen the six-part series written by <a href="http://search.bbc.co.uk/cgi-bin/search/results.pl?site=news&q=BLASTLAND+weekly+statistics+lesson&tab=ns" rel="nofollow">Michael Blastland on statistics on the BBC web site?

Andrew,

thanks—as always—for sharing your presentation. May I suggest a little technical modification in your "powerpoint" (a.k.a. LaTeX beamer) source code? If you put "handout" as an option next to the "documentclass", all effects in the presentation will be suppressed. Thus, the number of slides is reduced considerably, the file size is smaller, and the reader doesn't need to click through all effects…

Hence, your first line might look like this:

documentclass[13pt, handout]{beamer}

What do you think?

But if you do it this way, then when you walk into an unfamiliar computing environment to give a talk, you can simply navigate to your webpage and load the PDF. (Which indeed is what happened.)

Turning to the talk itself, it would be interesting to see a similar treatment for cases where the variables being interacted are continuous rather than categorical. This situation is harder to plot, to be sure, but as an advantage it would have fewer interaction terms (and presumably be easier to fit).