Content area
Full Text
Stat Papers (2014) 55:169186
DOI 10.1007/s00362-013-0545-7
REGULAR ARTICLE
Received: 13 April 2012 / Revised: 14 June 2013 / Published online: 5 July 2013
Springer-Verlag Berlin Heidelberg 2013
Abstract This paper extends an existing outlier-robust estimator of linear dynamic panel data models with xed effects, which is based on the median ratio of two consecutive pairs of rst-order differenced data. To improve its precision and robustness properties, a general procedure based on higher-order pairwise differences and their ratios is designed. The asymptotic distribution of this class of estimators is derived. Further, the breakdown point properties are obtained under contamination by independent additive outliers and by the patches of additive outliers, and are used to select the pairwise differences that do not compromise the robustness properties of the procedure. The proposed estimator is additionally compared with existing methods by means of Monte Carlo simulations.
Keywords Breakdown point Dynamic panel data Fixed effects
Pairwise differences Robust estimation
Mathematics Subject Classication (2000) 62F10 62F12 62F35
1 Introduction
In this paper, the robust estimation of dynamic panel data models with xed effects is considered, which have proven to be a very attractive modelling procedure in empirical applications. An important advantage of these models is that they allow to disentangle
ek (B)
CentER, Department of Econometrics & OR, Tilburg University, PO Box 90153, 5000 LE Tilburg,
The Netherlands
e-mail: [email protected]. Aquaro
e-mail: [email protected]
M. Aquaro P.
Robust estimation of dynamic xed-effects panel data models
Michele Aquaro Pavel
ek
123
170 M. Aquaro, P.ek
the persistent component due to the (time-invariant) unobserved heterogeneity from the one based on the dynamic behavior. The related literature is fairly extensive and dates back to more than 60years agofor an overview, see among others Harris et al. (2008). Unfortunately, almost all literature focuses on the models assuming that data are free of outlying or aberrant observations. This is often not the case in reality, not even in relatively reliable macroeconomic data as documented in Zaman et al. (2001). This issue is even more important in the case of panel data, where erroneous observations can be masked by the complex structure of the data.
Despite its relevance, the study of robust techniques for panel data seems to be rather limited. Few contributions are available for static models...