[EMAIL PROTECTED] wrote: > That's not what's bugging me. What I want to know is if it's justifiable > to control for things like parental occupation and disruptiveness in a > randomized study. This is ok for correlational research, but why would > you want to do it in a randomized study where such factors are already > eliminated through randomization? > > Randomization only eliminates things like this *on average*. If it made a different to the results, then that is prima facie evidence that randomization didn't eliminate the effect of those factors in this particular case.
Logistic regression is often used for either-or categorical outcomes because it amplifies the separation between the two categories in the predictions. Best, Chris -- Christopher D. Green Department of Psychology York University Toronto, ON M3J 1P3 Canada 416-736-5115 ex. 66164 [EMAIL PROTECTED] http://www.yorku.ca/christo/ ====================================== ---
