statsmodels.stats.proportion.binom_test¶

statsmodels.stats.proportion.binom_test(count, nobs, prop=0.5, alternative='two-sided')[source]¶

Perform a test that the probability of success is p.

This is an exact, two-sided test of the null hypothesis that the probability of success in a Bernoulli experiment is p.

Parameters:¶

count : {int, array_like}¶

the number of successes in nobs trials.

nobs : int¶

the number of trials or observations.

prop : float, optional¶

The probability of success under the null hypothesis, 0 <= prop <= 1. The default value is prop = 0.5

alternative : str in ['two-sided', 'smaller', 'larger']¶

alternative hypothesis, which can be two-sided or either one of the one-sided tests.

Returns:¶

p-value – The p-value of the hypothesis test

Return type:¶

float

Notes

This uses scipy.stats.binom_test for the two-sided alternative.