statsmodels.stats.weightstats._tconfint_generic

statsmodels.stats.weightstats._tconfint_generic(mean, std_mean, dof, alpha, alternative)

generic t-confint based on summary statistic

Parameters:

meanfloat or ndarray

Point estimate, for example the mean or the difference of means of two samples.

std_meanfloat or ndarray

Standard error of mean.

dofint or float

Degrees of freedom

alphafloat

Significance level for the confidence interval, coverage is 1-alpha.

alternativestr

The alternative hypothesis, H1, has to be one of the following

• ‘two-sided’ : H1: mean not equal to the null value.

• ‘larger’ : H1: mean larger than the null value.

• ‘smaller’ : H1: mean smaller than the null value.

Returns:

lowerfloat or ndarray

Lower confidence limit. This is -inf for the one-sided alternative “smaller”.

upperfloat or ndarray

Upper confidence limit. This is inf for the one-sided alternative “larger”.