statsmodels.sandbox.stats.multicomp.TukeyHSDResults¶

class statsmodels.sandbox.stats.multicomp.TukeyHSDResults(mc_object, results_table, q_crit, reject=None, meandiffs=None, std_pairs=None, confint=None, df_total=None, reject2=None, variance=None, pvalues=None)[source]¶

Results from Tukey HSD test, with additional plot methods

Can also compute and plot additional post-hoc evaluations using this results class.

Attributes:¶

rejectarray of bool, True if we reject Null for group pair

meandiffspairwise mean differences

confintconfidence interval for pairwise mean differences

std_pairsstandard deviation of pairwise mean differences

q_critcritical value of studentized range statistic at given alpha

halfwidthshalf widths of simultaneous confidence interval

pvaluesadjusted p-values from the HSD test

Notes

halfwidths is only available after call to plot_simultaneous.

Other attributes contain information about the data from the MultiComparison instance: data, df_total, groups, groupsunique, variance.

Methods

plot_simultaneous([comparison_name, ax, ...])	Plot a universal confidence interval of each group mean
summary()	Summary table that can be printed