In modern scientific research, data heterogeneity is commonly observed owing to the abundance of complex data. We propose a factor regression model for data with heterogeneous subpopulations. The proposed model can be represented as a decomposition of heterogeneous and homogeneous terms. The heterogeneous term is driven by latent factors in different subpopulations. The homogeneous term captures common variation in the covariates and shares common regression coefficients across subpopulations. Our proposed model attains a good balance between a global model and a group-specific model. The global model ignores the data heterogeneity, while the group-specific model fits each subgroup separately. We prove the estimation and prediction consistency for our proposed estimators, and show that it has better convergence rates than those of the group-specific and global models. We show that the extra cost of estimating latent factors is asymptotically negligible and the minimax rate is still attainable. We further demonstrate the robustness of our proposed method by studying its prediction error under a mis-specified group-specific model. Finally, we conduct simulation studies and analyze a data set from the Alzheimer's Disease Neuroimaging Initiative and an aggregated microarray data set to further demonstrate the competitiveness and interpretability of our proposed factor regression model.
The receiver operating characteristic (ROC) curve provides a comprehensive performance assessment of a continuous biomarker over the full threshold spectrum. Nevertheless, a medical test often dictates to operate at a certain high level of sensitivity or specificity. A diagnostic accuracy metric directly targeting the clinical utility is specificity at the controlled sensitivity level, or vice versa. While the empirical point estimation is readily adopted in practice, the nonparametric interval estimation is challenged by the fact that the variance involves density functions due to estimated threshold. In addition, even with a fixed threshold, many standard confidence intervals including the Wald interval for binomial proportion could have erratic behaviors. In this article, we are motivated by the superior performance of the score interval for binomial proportion and propose a novel extension for the biomarker problem. Meanwhile, we develop exact bootstrap and establish consistency of the bootstrap variance estimator. Both single-biomarker evaluation and two-biomarker comparison are investigated. Extensive simulation studies were conducted, demonstrating competitive performance of our proposals. An illustration with aggressive prostate cancer diagnosis is provided.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：