The authors would like to thank the two anonymous reviewers for their constructive feedback; the staff of the Irish Centre for High-End Computing for their helpful support; Daniel McMillen and Joris Pinkse for their willingness to answer questions by e-mail; and James LeSage for making data available for replication.
ESTIMATORS OF BINARY SPATIAL AUTOREGRESSIVE MODELS: A MONTE CARLO STUDY†
Version of Record online: 20 FEB 2014
© 2014 Wiley Periodicals, Inc.
Journal of Regional Science
Special Issue: Regional Competition, Agglomeration, and Housing Markets in China
Volume 54, Issue 4, pages 664–687, September 2014
How to Cite
Calabrese, R. and Elkink, J. A. (2014), ESTIMATORS OF BINARY SPATIAL AUTOREGRESSIVE MODELS: A MONTE CARLO STUDY. Journal of Regional Science, 54: 664–687. doi: 10.1111/jors.12116
- Issue online: 1 SEP 2014
- Version of Record online: 20 FEB 2014
- Manuscript Accepted: 30 DEC 2013
- Manuscript Revised: 4 OCT 2013
- Manuscript Received: 8 JAN 2013
The goal of this paper is to provide a cohesive description and a critical comparison of the main estimators proposed in the literature for spatial binary choice models. The properties of such estimators are investigated using a theoretical and simulation study, followed by an empirical application. To the authors' knowledge, this is the first paper that provides a comprehensive Monte Carlo study of the estimators' properties. This simulation study shows that the Gibbs estimator performs best for low spatial autocorrelation, while the recursive importance sampler performs best for high spatial autocorrelation. The same results are obtained by increasing the sample size. Finally, the linearized general method of moments estimator is the fastest algorithm that provides accurate estimates for low spatial autocorrelation and large sample size.