A High-Dimensional LM Test for Cross-Sectional Independence with Serially Correlated Data

Abstract

We develop a high-dimensional Lagrange multiplier (LM) test for cross-sectional independence in Gaussian panels with a common stationary, short-memory temporal covariance matrix. The statistic is based on the trace of the square of R, where R is the sample correlation matrix. When the cross-sectional and time dimensions grow proportionally, we derive explicit expansions for the null mean and variance in terms of temporal spectral moments. Random diagonal normalization produces a non-negligible centering correction, while squared sample correlations sharing a cross-sectional unit contribute an additional variance term. Both corrections vanish under temporal independence. We establish a central limit theorem under the null, consistency against fixed alternatives, and a Gaussian-shift limit with a detection boundary under local alternatives. Monte Carlo experiments examine the size and power of the oracle test and feasible versions that estimate the temporal spectral moments. The asymptotic theory applies to the oracle statistic; feasible procedures are evaluated numerically.