When Politics and Models Collide: Estimating Models of Multiparty Elections
Theory: The spatial model of elections can better be represented by using conditional logit models which consider the position of the parties in issue spaces than by multinomial logit models which only consider the position of voters in the issue space. The spatial model, and random utility models in general, suffer from a failure to adequately consider the substitutability of parties sharing similar or identical issue positions. Hypotheses: Multinomial logit is not necessarily better than successive applications of binomial logit. Conditional logit allows for considering more interesting political questions than does multinomial logit. The spatial model may not correspond to voter decision-making in multiple party settings. Multinomial probit allows for a relaxation of the IIA condition and this should improve estimates of the effect of adding or removing parties. Methods: Comparisons of binomial logit, multinomial logit, conditional logit, and multinomial probit on simulated data and survey data from multiparty elections. Results: Multinomial logit offers almost no benefits over binomial logit. Conditional logit is capable of examining movements by parties, whereas multinomial logit is not. Multinomial probit performs better than conditional logit when considering the effects of altering the set of choices available to voters. Estimation of multinomial probit with more than three choices is feasible.
Additional Information© 1998 Midwest Political Science Association. This is one of many joint papers by the authors on multiparty elections, the ordering of their names reflects alphabetic convention. Earlier versions of this research were presented at the Annual Meetings of the American Political Science Association, Chicago, IL, September 1 995 and at the Annual Political Methodology Summer Conference, Indianapolis, July, 1995. We thank John Aldrich, Nathaniel Beck, Simon Jackman, John Jackson, Jonathan Katz, Gary King, Dean Lacy, Eric Lawrence, Jan Leighley, Will Moore, Mitch Sanders, and Guy Whitten for their comments on earlier versions of this research, and Methodology Conference participants for their input. We also thank participants of the Southern California Political Economy Group for their discussion of this research on November 17, 1995 at the University of California--Irvine, and participants in the Second CIC Interactive Video Methods Seminar which was broadcast from the University of Minnesota on October 25, 1996. Alvarez thanks the John M. Olin Foundation for support of his research. Nagler thanks the NSF for grant SBR-9413939. Formerly SSWP 959.
Published - sswp959_-_published.pdf