The hypothesis of complete independence is necessary for many statistical inferences. Classical testing procedures can not be applied to test this hypothesis in high-dimensional data. In this paper, a simple test statistic is presented for testing complete independence in multivariate high dimensional normal data. Using the theory of martingales, the asymptotic normality of the test statistic is established. In order to evaluate the performance of the proposed test and compare it with existing procedures, a simulation study was conducted. The simulation results indicate that the proposed test has an empirical type-I error rate with an average relative error less than the available tests. An application of the proposed method for gene expression clinical prostate data is presented.

Nowadays, the observations in many scientific fields, including biological sciences, are often high dimensional, meaning the number of variables exceeds the number of samples. One of the problems in model-based clustering of these data types is the estimation of too many parameters. To overcome this problem, the dimension of data must be first reduced before clustering, which can be done through dimension reduction methods. In this context, a recent approach that is recently receiving more attention is the random Projections method. This method has been studied from theoretical and practical perspectives in this paper. Its superiority over some conventional approaches such as principal component analysis and variable selection method was shown in analyzing three real data sets.