Publication Type

Working Paper

Publication Date

11-2012

Abstract

This paper proposes an algorithm to estimate dynamic discrete choice models using aggregate market share data. The algorithm achieves a computational advantage by decomposing the complicated mapping between market shares and utility flows into two simpler ones. The first maps observed market shares to mean choice specific values, and the second then maps to mean utility flows. In the application, we estimate switching costs in the Medicare Part D market. Our results indicate a large switching cost of around $1,700, which implies an average welfare loss of $480 as enrollees choose to remain in sub-optimal plans to avoid switching costs.

Discipline

Economics | Health Economics

First Page

1

Last Page

47

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

http://www.mysmu.edu/faculty/jwyeo/papers/DynamicBerry_PartDSwitching2012.pdf

Share

COinS