330.626.11 ESTIMATING THE EFFECTS OF MENTAL HEALTH INTERVENTIONS IN NON-EXPERIMENTAL SETTINGS
Discusses the importance of the careful design of non-experimental studies, and the role of propensity scores in that design, with the main goal of providing practical guidance on the use of propensity scores in mental health research. Covers the primary ways of using propensity scores to adjust for confounders when estimating the effect of a particular “cause” or “intervention,” including weighting, subclassification, and matching. Examines issues such as how to specify and estimate the propensity score model, selecting covariates to include in the model, and diagnostics. Draws examples from school-based prevention research, drug abuse and dependence, and non-randomized treatment trials, among others. Primarily emphasizes non-experimental studies; however, also discusses applications to randomized trials. The second day provides hands-on experience with software for implementing propensity score analyses. Primary emphasis is on the MatchIt package for the open-source R statistical sof
After attending this course students will be able to: (1) Identify the characteristics of well-designed non-experimental studies; (2) Explain the role of propensity scores in non-experimental studies; (3) Specify and diagnose a propensity score model; and (4) Implement propensity score methods, including subclassification and matching.
Upon successfully completing this course, students will be able to:
Identify the characteristics of well-designed non-experimental studies
Explain the role of propensity scores in non-experimental studies
Specify and diagnose a propensity score model
Implement propensity score methods, including subclassification and matching
- Thu 06/14/2012 - Fri 06/15/2012
- Thursday 9:00 - 4:30
- Friday 9:00 - 4:30
Experience with linear and logistic regression.