17
2

Post-hoc and Anytime Valid Permutation and Group Invariance Testing

Abstract

We study post-hoc (ee-value-based) and post-hoc anytime valid inference for testing exchangeability and general group invariance. Our methods satisfy a generalized Type I error control that permits a data-dependent selection of both the number of observations nn and the significance level α\alpha. We derive a simple analytical expression for all exact post-hoc valid pp-values for group invariance, which allows for a flexible plug-in of the test statistic. For post-hoc anytime validity, we derive sequential pp-processes by multiplying post-hoc pp-values. In sequential testing, it is key to specify how the number of observations may depend on the data. We propose two approaches, and show how they nest existing efforts. To construct good post-hoc pp-values, we develop the theory of likelihood ratios for group invariance, and generalize existing optimality results. These likelihood ratios turn out to exist in different flavors depending on which space we specify our alternative. We illustrate our methods by testing against a Gaussian location shift, which yields an improved optimality result for the tt-test when testing sphericity, connections to the softmax function when testing exchangeability, and an improved method for testing sign-symmetry.

View on arXiv
Comments on this paper