Political Analysis Advance Access originally published online on September 3, 2007
Political Analysis 2007 15(4):387-405; doi:10.1093/pan/mpm022
| ||||||||||||||||||||||||||||||||||||||||||||||||||
Bayesian Approaches for Limited Dependent Variable Change Point Problems
Department of Political Science, University of Rochester, Rochester, NY 14620
e-mail: spln{at}mail.rochester.edu
Limited dependent variable (LDV) data are common in political science, and political methodologists have given much good advice on dealing with them. We review some methods for LDV "change point problems" and demonstrate the use of Bayesian approaches for count, binary, and duration-type data. Our applications are drawn from American politics, Comparative politics, and International Political Economy. We discuss the tradeoffs both philosophically and computationally. We conclude with possibilities for multiple change point work.
Author's note: This paper is a revised version of my "second-year paper" presented to the department in September 2005, and I thank attendees for feedback. For comments on an earlier draft, I am grateful to Kevin Clarke, David Firth, Jeff Gill, Kosuke Imai, Tasos Kalandrakis, Andrew Martin, Kevin Quinn, Curt Signorino, Randy Stone, and two anonymous referees. Any remaining errors and omissions remain mine and mine alone.