Glassman et al. (1990, JAMA 264: 1546-1549) published an article, "Smoking, smoking cessation, and major depression," in which they present data relevant to the relationships among persons' gender, smoking history, and psychiatric history. In the file SMOKE2.SAV, on Karl's SPSS Data Page, are the data (frequency counts) for gender (male vs female), smoking history (no, have been able to stop smoking vs yes, have stopped smoking), and depression (no, have not had a major depressive disorder vs yes, have had a major depressive disorder) for a sample of smokers.

Use SPSS to do a hierarchical log-linear analysis of these data. Develop a reduced model (having fewer than the 7 effects found in the fully saturated model). Use LOGLINEAR to obtain estimates of the parameters for the reduced model which you adopt. Use CROSSTABS to produce tables that will help you interpret any significant effects.

Write up your results in an APA-style results section and attach it to email to Karl. Be prepared to discuss your results in class and to show your statistical output to any interested parties.