REASSESSING THE STUDY OF SPLIT-TICKET VOTING

Burden and Kimball (1998) report that, by using the King estimation procedure for inferring individual-level behavior from aggregate data, they are the first to produce accurate estimates of split-ticket voting rates in congressional districts. There are, however, several reasons to doubt that their analysis produced accurate cross-level inferences. We show that the estimation technique is highly suspect in general and especially unhelpful with these particular data. Hence, their conclusions about split-ticket voting in 1988 should be regarded as dubious. We delineate the key steps and main barriers in performing an unimpeachable analysis of ticketsplitting using aggregate data. Wendy K. Tam Cho is Assistant Professor of Political Science and Statistics at the University of Illinois at UrbanaChampaign. Brian J. Gaines is Assistant Professor of Political Science at the University of Illinois at Urbana-Champaign. We would like to thank Bear Braumoeller, Bruce Cain, Michael Caldwell, Lawrence Cho, Christophe Crombez, Susan Jellissen, Masaru Kohno, Peter Nardulli, Brian Sala, and Jasjeet Sekhon for helpful comments. Cho also thanks the National Science Foundation (Grant No. SBR–9806448) for research support.