Title: Statistical inference for random coefficient dynamic panel data models
Authors: Remigijus Leipus - Vilnius University (Lithuania) [presenting]
Anne Philippe - Universite de Nantes (France)
Donatas Surgailis - Vilnius university - Institute of mathematics and informatics (Lithuania)
Vytaute Pilipauskaite - Vilnius University - Universite de Nantes (Lithuania)
Abstract: The purpose is to discuss nonparametric estimation of the distribution function of the autoregressive coefficient from a panel of random coefficient AR(1) data. Consistency and asymptotic normality of the empirical distribution function and a class of kernel density estimators, as number and length of panels increase to infinity, is established. The Kolmogorov-Smirnov goodness-of-fit test for simple and composite hypotheses of Beta distributed coefficient is discussed. A simulation study for goodness-of-fit testing examines the finite-sample performance. The corresponding tail-index estimator and its properties are provided.