← tsb playground · t-tests, chi-square, ANOVA, normality, correlation, Mann-Whitney U, Kolmogorov-Smirnov
ttest1samp
Test whether the mean of a sample equals a hypothesised population mean.
Returns { statistic, pvalue }. Mirrors
scipy.stats.ttest_1samp(a, popmean).
alternative option
Use alternative: "greater" or "less" for
one-tailed tests.
ttestInd (Welch's)
Compare means of two independent groups. Defaults to Welch's t-test
(unequal variances). Mirrors scipy.stats.ttest_ind.
ttestRel
Compare measurements on the same subjects before and after an
intervention. Mirrors scipy.stats.ttest_rel(a, b).
chi2Contingency
Test whether two categorical variables are independent using a
contingency table. Mirrors scipy.stats.chi2_contingency.
fOneway
Test whether two or more groups have equal population means.
F = between-group variance / within-group variance.
Mirrors scipy.stats.f_oneway(*groups).
jarqueBera
Test H₀: data is normally distributed, using sample skewness and
kurtosis. JB ~ χ²(2) under H₀.
Mirrors scipy.stats.jarque_bera(data).
pearsonr
Compute the Pearson product-moment correlation coefficient and its
p-value (H₀: r = 0). Mirrors scipy.stats.pearsonr(x, y).
spearmanr
Non-parametric rank-based correlation. Robust to outliers and
non-normal data. Mirrors scipy.stats.spearmanr(x, y).
mannWhitneyU
Non-parametric alternative to the independent t-test. Tests whether
one population tends to have larger values than another.
Mirrors scipy.stats.mannwhitneyu.
kstest
Test whether data follows a specified distribution (e.g. normal,
uniform). D = max|F_n(x) − F(x)|.
Mirrors scipy.stats.kstest(data, cdf).