9.8 Choose a research question that can be addressed with the data from Problem 7.4 using a logistic regression analysis. Explain which of the variables would be used as the outcome and which variables would be used as predictors. Fit the logistic regression model to address your research question. Fully interpret the results of the analysis, including the process you used to select the most parsimonious model and substantive interpretations of its parameter estimates.

9.9 Use the data set on arthritis (obtained from Michael Friendly’s web site, at http://

friendly.apps01.yorku.ca/psy6140/ex/logistic.htm), where improve = 1 or 2 indicates improvement (and improve = 0 indicates no improvement). Fit a model to predict whether the patient improves from the predictors of patient’s sex, treatment group, age

(a continuous variable), and any needed interactions. Fully interpret the results of the analysis, including the process you used to select the most parsimonious model and substantive interpretations of its parameter estimates.