No CrossRef data available.
Published online by Cambridge University Press: 04 January 2017
Political science researchers typically conduct an idiosyncratic search of possible model configurations and then present a single specification to readers. This approach systematically understates the uncertainty of our results, generates fragile model specifications, and leads to the estimation of bloated models with too many control variables. Bayesian model averaging (BMA) offers a systematic method for analyzing specification uncertainty and checking the robustness of one's results to alternative model specifications, but it has not come into wide usage within the discipline. In this paper, we introduce important recent developments in BMA and show how they enable a different approach to using the technique in applied social science research. We illustrate the methodology by reanalyzing data from three recent studies using BMA software we have modified to respect statistical conventions within political science.
Authors' note: A poster based on an earlier version of this paper was presented at the Society for Political Methodology Summer Conference, State College, PA, July 18–21, 2007. We thank James Adams, Benjamin G. Bishin, David W. Brady, Brandice Canes-Wrone, John F. Cogan, Jay K. Dow, James D. Fearon, and David D. Laitin for sharing their data and providing assistance with our replications of their work. We also thank John H. Aldrich, Michael C. Brady, Merlise Clyde, Josh Cutler, Scott de Marchi, Andrew Gelman, Daniel J. Lee, Efrén O. Pérez, Jill Rickershauser, David Sparks, Michael W. Tofias, T. Camber Warren, the editors, and two anonymous reviewers for helpful comments. All remaining errors are, of course, our own. Replication materials are available on the Political Analysis Web site.
Full text views reflects PDF downloads, PDFs sent to Google Drive, Dropbox and Kindle and HTML full text views.
* Views captured on Cambridge Core between 04th January 2017 - 27th January 2021. This data will be updated every 24 hours.