Bayesian Model Averaging in Economics.
Megan Baburek, MS Candidate, Department of Statistics,Colorado StateUniversity.
Friday, April 3, 2009
9:00 am, Weber 223
Due to the theoretical nature of many economic models, many of the variables are challenging to measure. Often the best we can do is to try to estimate these variables using several easier to measure predictors. Then model selection becomes an issue: which variables are important to include in the model? Bayesian Model Averaging (BMA) offers a way to deal with the uncertainty we face in model selection. Here I will provide a review of the basics of BMA. I will also provide an overview of how BMA has been used in economics. This will be illustrated with an example of how BMA can be used to determine important variables in economic growth models.
Advisor: Dr. Jennifer Hoeting
Member: Dr. Dan Cooley
Outside: Dr. Alexandra Bernasek (Economics)