Trimmed Likelihood-based Estimation in Binary Regression Models

Pavel Čížek

doi:10.17713/ajs.v35i2&3.368

Authors

Pavel Čížek Tilburg University, The Netherlands

DOI:

https://doi.org/10.17713/ajs.v35i2&3.368

Abstract

Binary-choice regression models such as probit and logit are typically estimated by the maximum likelihood method. To improve its robustness, various M-estimation based procedures were proposed, which however require bias corrections to achieve consistency and their resistance to outliers is relatively low. On the contrary, traditional high-breakdown point methods such as maximum trimmed likelihood are not applicable since they induce the separation of data and thus non-identification of estimates by trimming observations.
We propose a new robust estimator of binary-choice models based on a maximum symmetrically trimmed likelihood estimator. It is proved to be identified and consistent, and additionally, it does not create separation in the space of explanatory variables as the existing maximum trimmed likelihood. We also discuss asymptotic and robust properties of the proposed method and compare all methods by means of Monte Carlo simulations.

References

Albert, A., and Anderson, J. A. (1984). On the existence of maximum likelihood estimates in logistic regression models. Biometrika, 71, 1-10.

Bianco, A. M., and Yohai, V. J. (1996). Robust estimation in the logistic regression model. In H. Rieder (Ed.), Robust Statistics, Data Analysis, and Computer Intensive Methods (p. 17-34). New York: Springer.

Carroll, R. J., and Pederson, S. (1993). On robustness in the logistic regression model. Journal of Royal Statistical Society, B, 55, 693-706.

Christmann, A. (1994). Least median of weighted squares in logistic regression with large strata. Biometrika, 81, 413-417.

Copas, J. B. (1988). Binary regression models for contamination data. Journal of Royal Statistical Society, Ser. B, 50, 225-265.

Croux, C., Flandre, C., and Haesbroeck, G. (2002). The breakdown behavior of the maximum likelihood estimator in the logistic regression model. Statistics & Probability Letters, 60, 377-386.

Croux, C., and Haesbroeck, G. (2003). Implementing the Bianco and Yohai estimator for logistic regression. Computational Statistics and Data Analysis, 44, 273-295.

Genton, M. G., and Lucas, A. (2003). Comprehensive definitions of breakdown points for independent and dependent observations. Journal of Royal Statistical Society, B, 65, 81-94.

Gervini, D. (2005). Robust adaptive estimators for binary regression models. Journal of Statistical Planning and Inference, 131, 297-311.

Hausman, J. A., Abrevaya, J., and Scott-Morton, F. M. (1998). Misclassification of the dependent variable in a discrete-response setting. Journal of Econometrics, 87, 239-269.

Kordzakhia, N., Mishra, G. D., and Reiersølmoen, L. (2001). Robust estimation in the logistic regression model. Journal of Statistical Planning and Inference, 98, 211-223.

Müller, C. H., and Neykov, N. M. (2003). Breakdown points of trimmed likelihood estimators and related estimators in generalized linear models. Journal of Statistical Planning and Inference, 116, 503-519.

Stromberg, A. J., and Ruppert, D. (1992). Breakdown in nonlinear regression. Journal of the American Statistical Association, 87, 991-997.

Čížek, P. (2001, November). Robust estimation with discrete explanatory variables (CERGE-EI Working Papers No. wp183). CERGE-EI, Charles University, Prague.

Čížek, P. (2004, December). General trimmed estimation: robust approach to nonlinear and limited dependent variable models (Discussion Paper No. 130). Tilburg University, Center for Economic Research.

Čížek, P. (2005). Least trimmed squares in nonlinear regression under dependence. Journal of Statistical Planning and Inference, in press.