Citation:
Abstract:
An article by Barry C. Burden and David C. Kimball entitled “A New Approach to the Study of Ticket Splitting” was published in the September 1998 issue of the American Political Science Review. The empirical part of the article made use of an ecological inference technique developed by Gary King in his book, A Solution to the Ecological Inference Problem (Princeton University Press,1997). As the Burden-Kimball paper was going to press, Wendy K.Tam Cho and Brian J. Gaines submitted a critique of it to the APSR using data publicly archived by Burden and Kimball at the ICPSR. The Cho-Gaines paper criticized many aspects of the Burden-Kimball article, but focused primarily on the use of King's ecological inference method. The Cho-Gaines paper survived the review process and was accepted for publication, at which point the APSR Editor, Ada Finifter, permitted Burden-Kimball and King to submit responses. These responses made use of replication datasets provided by Cho and Gaines (but not available to their reviewers) and went through the review process as well. Both papers discredited the Cho-Gaines critique, but the Burden-Kimball paper also revealed that Cho and Gaines had failed to replicate Burden and Kimball’s analysis as they had claimed. This led Finifter to pull the Cho-Gaines paper from the publication pipeline and publish none of the papers. The following statement was offered to Review readers:
“Because of inaccuracies discovered during the prepublication process, ‘Reassessing the Study of Split-Ticket Voting,’ by Wendy K. Tam Cho and Brian J. Gaines, previously listed as forthcoming, has been withdrawn from publication” (December 2001 APSR).
This archive contains the material necessary for those who wish to review the entire case. The 56 files provided here include the Cho-Gaines paper and the rebuttals by Burden-Kimball and King, replication datasets provided by Cho and Gaines, and a decision letter from Finifter.
See the README for an overview, my concluding comment, and the entire archive here and in the ICPSR Replication Archive.