论文信息 - Almost Unbiased Estimation of the Poisson Regression Model

Almost Unbiased Estimation of the Poisson Regression Model

We derive expressions for the first-order bias of the MLE for a Poisson regression model and show how these can be used to adjust the estimator and reduce bias without increasing MSE. The analytic results are supported by Monte Carlo simulations and an empirical application.

D. Giles | Hui Feng

[1] D. Giles,et al. Finite-Sample Properties of the Maximum Likelihood Estimator for the Poisson Regression Model With Random Covariates , 2011 .

[2] Anne-Marie Gulde,et al. Exchange Rate Regimes : Choices and Consequences , 2009 .

[3] H. Friedl. Econometric Analysis of Count Data , 2002 .

[4] Kurt Brännäs,et al. Finite sample properties of estimators and tests in poisson regression models , 1992 .

[5] Norman E. Breslow,et al. Tests of Hypotheses in Overdispersed Poisson Regression and other Quasi-Likelihood Models , 1990 .

[6] Gary King. Statistical Models for Political Science Event Counts: Bias in Conventional Procedures and Evidence for the Exponential Poisson Regression Model , 1988 .

[7] D. Cox,et al. A General Definition of Residuals , 1968 .

[8] L. Shenton,et al. Higher Moments of a Maximum‐Likelihood Estimate , 1963 .

[9] J. Haldane,et al. THE SAMPLING DISTRIBUTION OF A MAXIMUM-LIKELIHOOD ESTIMATE , 1956 .

[10] M. Bartlett,et al. APPROXIMATE CONFIDENCE INTERVALSMORE THAN ONE UNKNOWN PARAMETER , 1953 .