This paper examines Bayesian model averaging as a means of improving the predictive performance of statistical models commonly encountered in the social and behavioral sciences. We demonstrate the utility of Bayesian model averaging for prediction in the social and behavioral sciences with three examples: Bayesian regression analysis, Bayesian logistic regression, and a recently developed approach for Bayesian structural equation modeling. In each case, the model-averaged estimates are shown to yield better prediction of the outcome of interest than any sub-model based on predictive coverage and the log-score rule.
Hier finden Sie weitere Informationen zu David Kaplan und seinem Vortrag in der Arbeitsgruppe Methoden und Evaluation/Qualitätssicherung.
04.02.2016 | 16:00 - 18:00
Seminarzentrum, Raum L 113