Pseudo-Gaussian and Rank-Based Tests for First-Order Superdiagonal Bilinear Models in Panel Data

Abstract

In this paper, locally asymptotically optimal (in the H´ajek-Le Cam sense) parametric, pseudo-Gaussian and rank-based procedures are proposed for the problem of testing randomness against first-order superdiagonal bilinear panel dependence (in large n and small T panels). Local powers and asymptotic relative efficiencies are computed and show that the van der Waerden version of our rank-based tests uniformly dominates. Small-sample performances are investigated via simulations and confirm the theoretical findings, they also demonstrate the remarkable performances of rank procedures based on data-driven scores.

Keywords

• panel data
• first-order superdiagonal bilinear model
• local asymptotic normality
• pseudo-Gaussian test
• rank test
• asymptotic relative efficiency