Maximum Likelihood Estimation of Models with Beta-Distributed Dependent Variables

Research in political science is often concerned with modeling dependent variables that are proportions. Proportions are relevant in a wide variety of substantive areas, including elections, the bureaucracy, and interest groups. Yet because most researchers rely upon an approach, OLS, that does not recognize key aspects of proportions, the conclusions we reach from normal models may not provide the best understanding of phenomena of interest in these areas. In this paper, I use Monte Carlo simulations to show that maximum likelihood estimation of these data using the beta distribution may provide more accurate and more precise results. I then present empirical analyses illustrating some of these differences.

[1]  R. Salisbury.  Interest Representation: The Dominance of Institutions , 1984, American Political Science Review.

[2]  K. Meier,et al.  The Politics of Gay and Lesbian Rights: Expanding the Scope of the Conflict , 1996, The Journal of Politics.

[3]  Lael R. Keiser,et al.  With Good Cause: Bureaucratic Discretion and the Politics of Child Support Enforcement , 1998 .

[4]  J. Brudney,et al.  Bureaucracy as a Representative Institution: Toward a Reconciliation of Bureaucratic Government and Democratic Theory , 1998 .

[5]  C. Franklin.  Eschewing Obfuscation? Campaigns and the Perception of U.S. Senate Incumbents , 1991, American Political Science Review.

[6]  Scott Gates,et al.  Donut Shops and Speed Traps: Evaluating Models of Supervision on Police Behavior , 1993 .

[7]  Jason Wittenberg,et al.  Making the Most Of Statistical Analyses: Improving Interpretation and Presentation , 2000 .

[8]  Jonathan N. Katz,et al.  What To Do (and Not to Do) with Time-Series Cross-Section Data , 1995, American Political Science Review.

[9]  R. Michael Alvarez,et al.  American Ambivalence Towards Abortion Policy: Development of a Heteroskedastic Probit Model of Competing Values , 1995 .

[10]  L. Atkeson.  Divisive Primaries and General Election Outcomes: Another Look at Presidental Campaigns , 1998 .

[11]  Sanford F. Schram,et al.  Without cause or effect: Reconsidering welfare migration as a policy problem , 1998 .

[12]  W. Mebane.  Coordination, Moderation, and Institutional Balancing in American Presidential and House Elections , 2000, American Political Science Review.

[13]  John M. Brehm,et al.  Are Americans Ambivalent Towards Racial Policies , 1997 .

[14]  D. Lowery,et al.  The Dominance of Institutions in Interest Representation: A Test of Seven Explanations , 1998 .

[15]  Allan L. McCutcheon,et al.  Cross-Level Inference , 1995 .

[16]  Craig B. Borkowf,et al.  Random Number Generation and Monte Carlo Methods , 2000, Technometrics.