statsmodels.stats.weightstats.DescrStatsW.ttost_mean¶
- DescrStatsW.ttost_mean(low, upp)[source]¶
test of (non-)equivalence of one sample
TOST: two one-sided t tests
null hypothesis: m < low or m > upp alternative hypothesis: low < m < upp
where m is the expected value of the sample (mean of the population).
If the pvalue is smaller than a threshold, say 0.05, then we reject the hypothesis that the expected value of the sample (mean of the population) is outside of the interval given by thresholds low and upp.
Last update:
Oct 29, 2024