Inference in Generalized Linear Models with Robustness to Misspecified Variances

• 成果类型: Article; Early Access
• 署名作者: De Santis, Riccardo; Goeman, Jelle J.; Hemerik, Jesse; Davenport, Samuel; Finos, Livio
• 署名单位: University of Padua; Leiden University; Leiden University Medical Center (LUMC); Leiden University - Excl LUMC; Erasmus University Rotterdam; Erasmus University Rotterdam - Excl Erasmus MC; University of California System; University of California San Diego
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2025.2491775
• 发表日期: 2025
• 关键词: behrens-fisher problem; heteroscedasticity; tests

摘要

Generalized linear models usually assume a common dispersion parameter, an assumption that is seldom true in practice. Consequently, standard parametric methods may suffer appreciable loss of Type I error control. As an alternative, we present a semi-parametric group-invariance method based on sign flipping of score contributions. Our method requires only the correct specification of the mean model, but is robust against any misspecification of the variance. We present tests for single as well as multiple regression coefficients. The test is asymptotically valid but shows excellent performance in small samples. We illustrate the method using RNA sequencing count data, for which it is difficult to model the overdispersion correctly. The method is available in the R library flipscores. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.