Far East Journal of Theoretical Statistics
Volume 20, Issue 2, Pages 179 - 196
(November 2006)
|
|
COMPARISON OF GMM WITH SECOND-ORDER LEAST SQUARES ESTIMATION
IN NONLINEAR MODELS
Taraneh Abarin (Canada) and Liqun Wang (Canada)
|
Abstract: Generalized method of moments (GMM) is an estimation technique
which estimates unknown parameters by matching theoretical moments with sample
moments. It may provide a poor approximation to the finite sample distribution
of the estimator. Moreover, increasing the number of moment conditions requires
substantial increase of the sample size. Second-order least squares (SLS)
estimation is an extension of the ordinary least squares method by adding to the
criterion function the distance of the squared response variable to its second
conditional moment. It is shown in this paper that the SLS is asymptotically
more efficient than the GMM when both use the same moment conditions. Moreover,
Monte Carlo simulation studies show that SLS performs better than the GMM
estimators using three or four moment conditions. |
Keywords and phrases: asymptotic efficiency, consistency, identifiability, least
squares method, method of moments, minimum distance estimator, nonlinear
regression. |
|
Number of Downloads: 286 | Number of Views: 867 |
|