Correcting the bias in the estimation of a dynamic ordered probit with fixed effects of self-assessed health status

This paper considers the estimation of a dynamic ordered probit with fixed effects, with an application to self-assessed health status. The estimation of nonlinear panel data models with fixed effects by MLE is known to be biased when T is not very large. The problem is specially severe in our model because of the dynamics and because it contains two fixed effects: one in the linear index equation, interpreted as unobserved health status, and another one in the cut points, interpreted as heterogeneity in reporting behavior. The contributions of this paper are twofold. Firstly this paper contributes to the recent literature on bias correction in nonlinear panel data models by applying and studying the finite sample properties of two of the existing proposals to the ordered probit case. The most direct and easily applicable correction to our model is not the best one and still has important biases in our sample sizes. Secondly, we contribute to the literature that study the determinants of Self-Assesed Health measures by applying the previous analysis on estimation methods to the British Household Panel Survey.