Journal article
A warning on separation in multinomial logistic models
Research & politics, Vol.5(2), p.205316801876951
04/2018
DOI: 10.1177/2053168018769510
Abstract
Oppenheim et al. (2015) provides the first empirical analysis of insurgent defection during armed rebellion, estimating a series of multinomial logit models of continued rebel participation using a survey of ex-combatants in Colombia. Unfortunately, many of the main results from this analysis are an artifact of separation in these data – that is, one or more of the covariates perfectly predicts the outcome. We demonstrate that this can be identified using simple cross tabulations. Furthermore, we show that Oppenheim et al.’s (2015) results are not supported when separation is explicitly accounted for. Using a generalization of Firth’s (1993) penalized-likelihood estimator – a well-known solution for separation – we are unable to reproduce any of their conditional results. While our (re-)analysis focuses on Oppenheim et al. (2015), this problem appears in other research using multinomial logit models as well. We believe that this is both because the discussion on separation in political science has primarily focused on binary-outcome models, and because software (Stata and R) does not warn researchers about seperation in multinomial logit models. Therefore, we encourage researchers using multinomial logit models to be especially vigilant about separation, and discuss simple red flags to consider.
Details
- Title: Subtitle
- A warning on separation in multinomial logistic models
- Creators
- Scott J Cook - Department of Political Science, Texas A&M University, College Station, USAJohn Niehaus - Department of Political Science, Texas A&M University, College Station, USASamantha Zuhlke - University of Iowa, School of Planning and Public Affairs
- Resource Type
- Journal article
- Publication Details
- Research & politics, Vol.5(2), p.205316801876951
- DOI
- 10.1177/2053168018769510
- ISSN
- 2053-1680
- eISSN
- 2053-1680
- Publisher
- SAGE Publications
- Language
- English
- Date published
- 04/2018
- Academic Unit
- Center for Social Science Innovation; Public Policy Center (Archive); School of Planning and Public Affairs
- Record Identifier
- 9984118245802771
Metrics
30 Record Views