Bun, Maurice J. G.: Bias Correction in the Dynamic Panel Data Model with a Nonscalar Disturbance Covariance Matrix
World Conference Econometric Society, 2000, Seattle

Maurice J. G. Bun, University of Amsterdam
Bias Correction in the Dynamic Panel Data Model with a Nonscalar Disturbance Covariance Matrix
Session: C-8-10  Monday 14 August 2000  by Bun, Maurice J. G.
By using asymptotic expansion techniques approximation formulae are developed for the bias of ordinary and generalized Least Squares Dummy Variable (LSDV) estimators in dynamic panel data models. Earlier results on bias approximation in first-order stable dynamic panel data models are extended to higher-order dynamic models with general disturbance covariance structure. The focus is on estimation of both short- and long-run coefficients. The results show that proper modelling of the disturbance covariance structure is indispensable. The bias approximations are used to construct bias corrected estimators which are then applied to quarterly data from 14 European Union countries. Money demand functions for M1, M2 and M3 are estimated for the EU area as a whole for the period 1991:I-1995:IV. The empirical results show that in general plausible long-run effects are obtained by the bias corrected estimators. Moreover, bias correction can be substantial underlining the importance of more refined estimation techniques. Also the efficiency gains by exploiting the heteroscedasticity and cross-correlation patterns between countries are considerable.
Submitted paper full-text in .pdf


File created by Jurgen Doornik with eswc2000.ox on 2-01-2001