Tests for covariance matrices, particularly for high dimensional data

Test statistics for sphericity and identity of the covariance matrix are presented, when the data are multivariate normal and the dimension, p, can be larger than the sample size, n. The statistics, derived under very general conditions, follow an approximate normal distribution for large p, also when p >> n. Simulation results, particularly emphasizing the case when p can be much larger than n, show that the proposed statistics are accurate for both size control and power. A discussion of the commonly used assumptions for high dimensional set up is also given, with the conclusions applicable in general as well as in the special case of high dimensional covariance testing