statsmodels.stats.weightstats._tconfint_generic¶

statsmodels.stats.weightstats._tconfint_generic(mean, std_mean, dof, alpha, alternative)[source]¶

generic t-confint based on summary statistic

Parameters:¶

mean : float or ndarray¶

Value, for example mean, of the first sample.

std_mean : float or ndarray¶

Standard error of the difference value1 - value2

dof : int or float¶

Degrees of freedom

alpha : float¶

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

alternative : str¶

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

• ’two-sided’ : H1: value1 - value2 - diff not equal to 0.

• ’larger’ : H1: value1 - value2 - diff > 0

• ’smaller’ : H1: value1 - value2 - diff < 0

Returns:¶

• lower (float or ndarray) – Lower confidence limit. This is -inf for the one-sided alternative “smaller”.

• upper (float or ndarray) – Upper confidence limit. This is inf for the one-sided alternative “larger”.