| Session Title: Treating Data According to Purpose: Frequentist Versus Bayesian Analyses |
| Skill-Building Workshop 619 to be held in Calhoun Room on Friday, November 9, 1:55 PM to 3:25 PM |
| Sponsored by the Quantitative Methods: Theory and Design TIG |
| Presenter(s): |
| J Michael Menke, University of Arizona, menke@u.arizona.edu |
| Abstract: In situations where clinical trials or long-term repeated sampling cannot be done or assumed to be done, classical research design and analysis are impossible. Evaluation research and program evaluation designs may help improve inference, but analytic methods are also essential to good inference and better-informed decisions. By comparing classical and Bayesian analytic techniques on data that are normally distributed versus those that deviate from normalcy, we may see how significance testing, parameter estimation, and other inferences may inform decisions. |