Post-hocs API reference

posthoc_conover(a[, val_col, group_col, ...])	Post hoc pairwise test for multiple comparisons of mean rank sums (Conover´s test).
posthoc_dunn(a[, val_col, group_col, ...])	Post hoc pairwise test for multiple comparisons of mean rank sums (Dunn's test).
posthoc_nemenyi(a[, val_col, group_col, ...])	Post hoc pairwise test for multiple comparisons of mean rank sums (Nemenyi's test).
posthoc_nemenyi_friedman(a[, y_col, ...])	Calculate pairwise comparisons using Nemenyi post hoc test for unreplicated blocked data.
posthoc_conover_friedman(a[, y_col, ...])	Calculate pairwise comparisons using Conover post hoc test for unreplicated blocked data.
posthoc_siegel_friedman(a[, y_col, ...])	Siegel and Castellan´s All-Pairs Comparisons Test for Unreplicated Blocked Data.
posthoc_miller_friedman(a[, y_col, ...])	Miller´s All-Pairs Comparisons Test for Unreplicated Blocked Data.
posthoc_npm_test(a[, val_col, group_col, ...])	Calculate pairwise comparisons using Nashimoto and Wright´s all-pairs comparison procedure (NPM test) for simply ordered mean ranksums.
posthoc_durbin(a[, y_col, group_col, ...])	Pairwise post hoc test for multiple comparisons of rank sums according to Durbin and Conover for a two-way balanced incomplete block design (BIBD).
posthoc_anderson(a[, val_col, group_col, ...])	Anderson-Darling Pairwise Test for k-samples.
posthoc_quade(a[, y_col, group_col, ...])	Calculate pairwise comparisons using Quade's post hoc test for unreplicated blocked data.
posthoc_vanwaerden(a[, val_col, group_col, ...])	Van der Waerden's test for pairwise multiple comparisons between group levels.
posthoc_tukey_hsd(a[, val_col, group_col, sort])	Pairwise comparisons with TukeyHSD confidence intervals.
posthoc_ttest(a[, val_col, group_col, ...])	Pairwise T test for multiple comparisons of independent groups.
posthoc_mannwhitney(a[, val_col, group_col, ...])	Pairwise comparisons with Mann-Whitney rank test.
posthoc_wilcoxon(a[, val_col, group_col, ...])	Pairwise comparisons with Wilcoxon signed-rank test.
posthoc_scheffe(a[, val_col, group_col, sort])	Scheffe's all-pairs comparisons test for normally distributed data with equal group variances.
posthoc_tamhane(a[, val_col, group_col, ...])	Tamhane's T2 all-pairs comparison test for normally distributed data with unequal variances.
posthoc_tukey(a[, val_col, group_col, sort])	Performs Tukey's all-pairs comparisons test for normally distributed data with equal group variances.
posthoc_dscf(a[, val_col, group_col, sort])	Dwass, Steel, Critchlow and Fligner all-pairs comparison test for a one-factorial layout with non-normally distributed residuals.
posthoc_dunnett(a[, val_col, group_col, ...])	Dunnett's test [1, 2, 3] for multiple comparisons against a control group, used after parametric ANOVA.
posthoc_dunnett_t3(a[, val_col, group_col, sort])	Dunnett's T3 all-pairs comparison test for normally distributed data with unequal group variances.
posthoc_games_howell(a[, val_col, ...])	Games-Howell all-pairs comparison test for normally distributed data with unequal group variances.
posthoc_lsd(a[, val_col, group_col, ...])	Fisher's Least Significant Difference (LSD) all-pairs comparison test for normally distributed data with equal group variances, following a parametric ANOVA [1]_.
posthoc_snk(a[, val_col, group_col, sort])	Student-Newman-Keuls (SNK) all-pairs comparison test for normally distributed data with equal group variances, following a parametric ANOVA [1]_, [2]_, [3]_.
posthoc_duncan(a[, val_col, group_col, sort])	Duncan's multiple range test for normally distributed data with equal group variances, following a parametric ANOVA [1]_.
posthoc_median(a[, val_col, group_col, ...])	Brown-Mood all-pairs median test, a nonparametric alternative to Kruskal-Wallis-type all-pairs tests robust to outliers and skew [1]_.
posthoc_steel(a[, val_col, group_col, ...])	Steel's many-to-one rank test [1]_, a nonparametric alternative to Dunnett's test for comparisons of several treatment groups against one control group.
posthoc_demsar(a[, y_col, group_col, ...])	Demsar's many-to-one test for unreplicated blocked data [1]_, comparing several treatments against one control (e.g. a baseline algorithm) across a set of blocks (e.g. datasets), based on Friedman-type ranks.