|Date:||Thursday, March 27, 2014|
In this study we proposed a generalization of the Second-Order Least Squares (SLS) in linear dynamic panel data model. The SLS was introduced by Wang (2003, 2004). We used a semiparametric framework where the estimation is based only on the first two conditional moments of response variable given the explanatory variables. There is no need to specify the distribution of the error components. The SLS approach can be considered as a compromise between the Random Effect (RE) and Fixed Effect (FE) approaches.
We showed that the SLS estimator is consistent and asymptotically normal for large $N$ and finite $T$ under fairly general regularity conditions. Moreover, we showed that the optimal SLS estimator reaches a semiparametric efficiency bound. A specification test was developed for the first time to be used whenever the SLS is applied to real data. Our Monte Carlo simulations showed that the optimal SLS estimator performs satisfactorily in finite sample situations compared to the first-differenced GMM and the random effects pseudo ML estimators. The results apply under stationary/nonstationary process and with/without exogenous regressors. The performance of the optimal SLS is robust under near-unit root case. Finally, the practical usefulness of the optimal SLSE was examined by an empirical study on the U.S. airfares.
Statistics seminar: Kevin Fraser — Thursday, March 1 at 2:45 p.m., 204 Robson Hall.
Statistics seminar: Jonathan Foord — Thursday, March 15 at 2:45 p.m., 301 Biological Sciences.
Statistics seminar: Forough Khadem — Thursday, March 22 at 2:45 p.m., 301 Biological Sciences.
PIMS lecture: Troy Day — Thursday, March 22 at 4 p.m., Robert Schultz Theatre.