🤖 AI Summary
This paper addresses joint testing of the mean vector and covariance matrix under a uniform block structure in high-dimensional data with missing observations. Method: We develop the first unified statistical inference framework accommodating missing data, introducing a novel block-wise Hadamard product representation for uniformly structured block matrices. This enables closed-form expressions for the likelihood ratio and information statistics, along with their exact null distributions. We further propose an FDP-controlled simultaneous marginal mean testing procedure. Contribution/Results: Theoretical analysis and extensive simulations demonstrate accurate distributional characterization of test statistics, robust and reliable FDP control, and strong robustness against perturbations in the covariance structure and arbitrary missingness mechanisms. The method is successfully applied to hypothesis testing in high-dimensional neuroimaging data, substantially broadening the practical applicability of block-structured covariance models in high-dimensional inference.
📝 Abstract
A block covariance structure is widely observed across large-scale and high-dimensional datasets in diverse fields such as biology, medicine, engineering, economics, and finance. This pattern entails partitioning a covariance matrix into uniform blocks, where each block exhibits equal variances and covariances. The importance of uniform-block structures lies in their ubiquity, interpretability, and ability to accommodate high dimensionality and data missingness. Despite their prevalence, statistical hypothesis testing under uniform-block covariance structures remains largely unexplored, and unknown statistical properties limit their application in research. To address this gap, we develop a comprehensive framework for joint hypothesis tests of both covariance and mean structures, leveraging a novel block Hadamard product representation of uniform-block matrices. Specifically, we derive closed-form likelihood ratio test statistics and information statistics, explicitly establishing their null distributions. Additionally, we perform simultaneous marginal mean tests under a procedure that controls the false discovery proportion (FDP). Extensive simulations validate the consistency between theoretical and empirical distributions of the joint test statistics, assess the performance of the proposed FDP control procedure, and evaluate the robustness of the joint test statistics against structural disruptions and missing data. Lastly, we apply our methodology to hypothesis testing in a high-dimensional imaging dataset.