Hostname: page-component-84b7d79bbc-x5cpj Total loading time: 0 Render date: 2024-07-31T21:12:36.973Z Has data issue: false hasContentIssue false
  • English
  • Français

Bias in Conditional and Unconditional Fixed Effects Logit Estimation

Published online by Cambridge University Press:  04 January 2017

Ethan Katz
Ethan Katz*
Affiliation:
Center for Basic Research in the Social Sciences, Harvard University, 34 Kirkland Street, Cambridge, Massachusetts 02138. e-mail: ekatz@post.harvard.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

Fixed-effects logit models can be useful in panel data analysis, when N units have been observed for T time periods. There are two main estimators for such models: unconditional maximum likelihood and conditional maximum likelihood. Judged on asymptotic properties, the conditional estimator is superior. However, the unconditional estimator holds several practical advantages, and therefore I sought to determine whether its use could be justified on the basis of finite-sample properties. In a series of Monte Carlo experiments for T < 20, I found a negligible amount of bias in both estimators when T ≥ 16, suggesting that a researcher can safely use either estimator under such conditions. When T < 16, the conditional estimator continued to have a very small amount of bias, but the unconditional estimator developed more bias as T decreased.

Type
Research Article
Information
Political Analysis , Volume 9 , Issue 4 , 2001 , pp. 379 - 384
Copyright
Copyright © 2001 by the Society for Political Methodology 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Andersen, Erling Bernhard. 1970. “Asymptotic Properties of Conditional Maximum-Likelihood Estimators.” Journal of the Royal Statistical Society 32: 283–301.Google Scholar
Andersen, Erling Bernhard. 1973. Conditional Inference and Models for Measuring. Copenhagen: Mentalhygiejnisk Forsknings Institut.Google Scholar
Beck, Nathaniel, and Katz, Jonathan. 2001. “Throwing Out the Baby with the Bath Water.” International Organization 55: 487–496.Google Scholar
Chamberlain, Gary. 1980. “Analysis of Covariance with Qualitative Data.” Review of Economic Studies 47: 225–238.Google Scholar
Green, Donald P., Kim, Soo Yeon, and Yoon, David H. 2001. “Dirty Pool.” International Organization 55: 441–468.CrossRefGoogle Scholar
Hsiao, Cheng. 1986. Analysis of Panel Data. New York: Cambridge University Press.Google Scholar
Hamerle, Alfred, and Ronning, Gerd. 1995. “Panel Analysis for Qualitative Variables.” In Handbook of Statistical Modeling for the Social and Behavioral Sciences, eds. Arminger, Gerhard, Clogg, Clifford C., and Sobel, Michael E. New York: Plenum Press.Google Scholar
Heckman, James. 1981. “The Incidental Parameters Problem and the Problem of Initial Conditions in Estimating a Discrete Time-Discrete Data Stochastic Process.” In Structural Analysis of Discrete Data, eds. Manski, Charles F. and McFadden, Daniel. Cambridge, MA: MIT Press.Google Scholar
King, Gary. 2001. “Proper Nouns and Methodological Propriety: Pooling Dyads in International Relations Data.” International Organization 55: 497–507.Google Scholar
McCullagh, P., and Nelder, J. A. 1989. Generalized Linear Models. New York: Chapman & Hall.CrossRefGoogle Scholar
Neyman, J., and Scott, Elizabeth L. 1948. “Consistent Estimates Based on Partially Consistent Observations.” Econometrica 16: 1–32.CrossRefGoogle Scholar
Wright, Benjamin D., and Douglas, Graham A. 1977. “Conditional Versus Unconditional Procedures for Sample-Free Item Analysis.” Educational and Psychological Measurement 37: 573–586.CrossRefGoogle Scholar