Dealing with Separation in Logistic Regression Models

  title={Dealing with Separation in Logistic Regression Models},
  author={Carlisle Rainey},
When facing small numbers of observations or rare events, political scientists often encounter separation, in which explanatory variables perfectly predict binary events or non-events. In this situation, maximum likelihood provides implausible estimates and the researcher might want incorporate some form of prior information into the model. The most sophisticated research uses Jeffreys’ invariant prior to stabilize the estimates. While Jeffreys’ prior has the advantage of being automatic, I… CONTINUE READING
4 Citations
54 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 54 references

On the Existence of Maximum Likelihood Estimates in Logistic Regression Models.

  • A. Albert, J. A. Anderson
  • Biometrika
  • 1984
Highly Influential
7 Excerpts

A Market-Based Model of State Supreme Court News: Lessons from Captial Cases.

  • Vining, Jr., L Richard, Teena Wilhelm, Jack D. Collens
  • State Politics and Policy Quarterly
  • 2015

A market - based model of state Supreme Court news : Lessons from capital cases

  • Alex. Weisiger
  • State Politics and Policy Quarterly
  • 2015

From Open Secrets to Secret Voting: Democratic Electoral Reforms and Voter Autonomy

  • Mares, Isabela.
  • Cambridge Studies in Comparative Politics…
  • 2015

Questioning the Effect of Nuclear Weapons on Conflict.

  • Bell, S Mark, Nicholas L. Miller
  • Journal of Conflict Resolution
  • 2015

Security Commitments and Nuclear Proliferation.

  • Reiter, Dan
  • Foreign Policy Analysis
  • 2014

Talking Peace: IAEA Technical Cooperation and Nuclear Proliferation.

  • Brown, L Robert, Jeffrey M. Kaplow
  • Journal of Conflict Resolution
  • 2014

Similar Papers

Loading similar papers…