Title: Robust estimation and moment selection in dynamic fixed-effects panel data models
Authors: Pavel Cizek - Tilburg University (Netherlands) [presenting]
Michelle Aquaro - University of Warwick (United Kingdom)
Abstract: The aim is to extend an existing outlier-robust estimator of linear dynamic panel data models with fixed effects, which is based on the median ratio of two consecutive pairs of the first-differenced data. To improve its precision and robust properties, a general procedure based on many pairwise differences and their ratios is designed. The evaluated ratios are combined by means of the proposed two-step GMM estimator, which newly relies on the weighting scheme reflecting both the variance and bias of the moment equations; the bias is assumed to stem from the outliers and data contamination and needs to be numerically approximated and estimated. Additionally, a robust criterion for selecting the number of moment conditions is proposed. The asymptotic distribution as well as robust properties of the estimator are derived; the latter are obtained both under contamination by independent additive outliers and the patches of additive outliers. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.