An assumption-free exact test for fixed-design linear models with exchangeable errors. (30th September 2020)

• Record Type: Journal Article
• Authors: Lei, Lihua; Bickel, Peter J
• Is Part Of: Biometrika. Volume 108:Number 2(2021)
• Page Start: 397
• Page End: 412
• Publication Date: 2020-09-30
• Subjects: Assumption-free test -- Exact test -- Fixed design -- Linear hypothesis -- Linear model -- Marginal rank test -- Nonlinear travelling salesman problem; Biometry -- Periodicals; 570.1519505
• DOI: 10.1093/biomet/asaa079
• Languages: English
• ISSNs: 0006-3444

Abstract

Summary: We propose the cyclic permutation test to test general linear hypotheses for linear models. The test is nonrandomized and valid in finite samples with exact Type I error $\alpha$ for an arbitrary fixed design matrix and arbitrary exchangeable errors, whenever $1 / \alpha$ is an integer and $n / p \geqslant 1 / \alpha - 1$, where $n$ is the sample size and $p$ is the number of parameters. The test involves applying the marginal rank test to $1 / \alpha$ linear statistics of the outcome vector, where the coefficient vectors are determined by solving a linear system such that the joint distribution of the linear statistics is invariant with respect to a nonstandard cyclic permutation group under the null hypothesis. The power can be further enhanced by solving a secondary nonlinear travelling salesman problem, for which the genetic algorithm can find a reasonably good solution. Extensive simulation studies show that the cyclic permutation test has comparable power to existing tests. When testing for a single contrast of coefficients, an exact confidence interval can be obtained by inverting the test.