Simple solutions to the initial conditions problem in dynamic, nonlinear panel data models with unobserved heterogeneity

Journal of Applied Econometrics - Tập 20 Số 1 - Trang 39-54 - 2005
Jeffrey M. Wooldridge1
1Department of Economics, Michigan State University, USA

Tóm tắt

AbstractI study a simple, widely applicable approach to handling the initial conditions problem in dynamic, nonlinear unobserved effects models. Rather than attempting to obtain the joint distribution of all outcomes of the endogenous variables, I propose finding the distribution conditional on the initial value (and the observed history of strictly exogenous explanatory variables). The approach is flexible, and results in simple estimation strategies for at least three leading dynamic, nonlinear models: probit, Tobit and Poisson regression. I treat the general problem of estimating average partial effects, and show that simple estimators exist for important special cases. Copyright © 2005 John Wiley & Sons, Ltd.

Từ khóa


Tài liệu tham khảo

10.1016/0304-4076(94)01641-C

10.1016/0304-4076(82)90095-1

10.2307/2297968

10.1016/0304-4076(94)01642-D

10.1016/S0304-4076(03)00095-2

10.2307/1912110

10.1016/S0304-4076(98)00009-8

Blundell RW, 1991, Initial conditions and efficient estimation in dynamic panel data models, Annales d'Economie et de Statistique, 20, 109

10.2307/2297110

10.2307/1391799

10.1198/073500101316970377

10.1017/CBO9780511493140.005

10.1016/S0304-4076(99)00013-5

10.2307/1911191

Heckman JJ, 1981, Structural Analysis of Discrete Data with Econometric Applications, 179

10.1016/0304-4076(93)90038-7

10.1111/1468-0262.00139

Hsiao C, 1986, Analysis of Panel Data

10.1002/jae.3950070407

10.1017/S0266466600006125

10.1016/S0165-1765(00)00230-5

Wooldridge JM, 2002, Econometric Analysis of Cross Section and Panel Data