For this assignment you can use any statistical software you are
familiar with or use R. The objective is to find a set of variables that would predict response to citalopram.
Citalopram is an antidepressant. It is abbreviated as CIT in the data. These data come from STAR*D experiment conducted by NIMH.
- Read about the study protocol. Protocol►
- Download data. Use instructor's last name as password. Must enter password twice.
- Summarize the data.
- Select a set of variables and construct a logistic regression
model to predict success of CIT.
- Check assumptions of the model through visual plots, including:
- the residuals of the model are nearly normal,
- the variability of the residuals is nearly constant,
- the residuals are independent, and
- each variable is linearly related to the outcome
- Describe what predicts success of CIT.
- Describe how well the model predicts response to CIT.
See Bushra GM's response to assignment
See work of Jamie and Shruti Read►
For additional information (not part of the required reading), please see the following links:
- Regression using R Read►
- Statistical learning with R
- Open introduction to statistics
This page is part of the course on Comparative Effectiveness by Farrokh Alemi PhD Home►