Notebooks

## Two-Sample Tests

26 Oct 2019 14:14

That is, statistical tests for whether two samples came from the same distribution.

(If you came here because a search engine directed you while you were looking for recipes on how to do specific test, like a $t$ test, Mann-Whitney, etc., sorry.)

Recommended (totally inadequate):
• EunYi Chung, Joseph P. Romano, "Exact and asymptotically robust permutation tests", Annals of Statistics 41 (2013): 484--507, arxiv:1304.5939
• Bharath K. Sriperumbudur, Kenji Fukumizu, Arthur Gretton, Bernhard Schölkopf, and Gert R. G. Lanckriet, "On the empirical estimation of integral probability metrics", Electronic Journal of Statistics 6 (2012): 1550--1599
• Susan Wei, Chihoon Lee, Lindsay Wichers, Gen Li, J.S. Marron, "Direction-Projection-Permutation for High Dimensional Hypothesis Tests", arxiv:1304.0796
• Makoto Yamada, Taiji Suzuki, Takafumi Kanamori, Hirotaka Hachiya, Masashi Sugiyama, "Relative Density-Ratio Estimation for Robust Distribution Comparison", Neural Computation 25 (2013): 1324--1370 [This is not the relative density between $p$ and $q$ in the Handcock-Morris sense, just the ratio between $p$ and $ap+(1-a)q$, for adjustable $a$. (This is to keep the density ratio from going to infinite anywhere.) The thing seems a bit hackish, but still worth considering...]