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, alpha=None, group_t=None, group_c=None)

Results from Tukey HSD test, with additional plot methods

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

Attributes:

rejectndarray

Boolean array indicating whether the null hypothesis is rejected for each group pair.

meandiffsndarray

Pairwise mean differences.

confintndarray

Confidence intervals for the pairwise mean differences.

std_pairsndarray

Standard deviations of the pairwise mean differences.

q_critfloat or ndarray

Critical value or values of the studentized range statistic at the specified significance level.

halfwidthsndarray

Half widths of the simultaneous confidence intervals. This attribute is available after calling plot_simultaneous.

pvaluesndarray

Adjusted p-values from the HSD test.

reject2ndarray

Alternative boolean rejection decisions based on the confidence intervals.

df_totalfloat or ndarray

Total degrees of freedom used for each pairwise comparison.

df_total_hsdfloat

Total degrees of freedom used for the HSD critical value.

variancefloat or ndarray

Variance estimate or estimates used in the pairwise comparisons.

alphafloat

Significance level used for the test.

group_tndarray

Treatment group label for each pairwise comparison.

group_cndarray

Control group label for each pairwise comparison.

datandarray

Original response data from the MultiComparison instance.

groupsndarray

Original group labels from the MultiComparison instance.

groupsuniquendarray

Unique group labels from the MultiComparison instance.

Methods

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

Methods

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