Category-Adaptive Variable Screening for Ultra-High Dimensional Heterogeneous Categorical Data

The populations of interest in modern studies are very often heterogeneous. The population heterogeneity, the qualitative nature of the outcome variable and the high dimensionality of the predictors pose significant challenge in statistical analysis. In this article, we introduce a category-adaptive screening procedure with high-dimensional heterogeneous data, which is to detect category-specific important covariates. The proposal is a model-free approach without any specification of a regression model and an adaptive procedure in the sense that the set of active variables is allowed to vary across different categories, thus making it more flexible to accommodate heterogeneity. For response-selective sampling data, another main discovery of this article is that the proposed method works directly without any modification. Under mild regularity conditions, the newly procedure is shown to possess the sure screening and ranking consistency properties. Simulation studies contain supportive evidence that the proposed method performs well under various settings and it is effective to extract category-specific information. Applications are illustrated with two real datasets. Supplementary materials for this article are available online.