Title: Large sample properties of an IV estimator based on nonlinear moment conditions
Authors: Andrew Adrian Yu Pua - Xiamen University (China)
Markus Fritsch - University of Passau (Germany) [presenting]
Joachim Schnurbus - University of Passau (Germany)
Abstract: An instrumental variables (IV) estimator based is proposed on nonlinear (in parameters) moment conditions for estimating linear dynamic panel data models and derive the large sample properties of the estimator. We impose the following assumptions: (i) the only explanatory variable in the model is one lag of the dependent variable; (ii) the true lag parameter is smaller or equal to one in absolute value; (iii) the cross-section dimension is large; and (iv) the time series dimension is either fixed or large. Estimation of the lag parameter involves solving a quadratic equation, and we find that the lag parameter is point identified in the unit root case; otherwise, two distinct roots (solutions) result. We propose a selection rule that identifies the consistent root asymptotically in the latter case. We derive the asymptotic distribution of the estimator for the unit root case and the case when the absolute value of the lag parameter is smaller than one.