I lost track of who originally asked the question, but I have a web page that talks about selection of a control group. Part of the page discusses matching and crossover designs, which may prove helpful for understanding paired data in a different context than before/after experiments. I also cite some published examples of matching and crossover designs where the full text is available for free on the net. My page is at
http://www.childrens-mercy.org/stats/journal/apples.asp I'm hoping to turn this web page and some related web pages into a book about statistical evidence in medical journals. So if anyone has comments, suggestions, or feedback about this page, I would greatly appreciate it. Steve Simon, [EMAIL PROTECTED], Standard Disclaimer. The STATS web page has moved to http://www.childrens-mercy.org/stats. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
