Clopper-Pearson intervals can be used to calculate the Confidence Intervals of Bernoulli trials, particularly if $np < 5$ or $n(1-p) < 5$ (with $n$ being the number of trials and $p$ the chance of success). ## In Excel For the lower bound: ``` BETA.INV($ALPHA / 2, $X, $N - $X + 1) ``` And for the upper bound: ``` BETA.INV(1 - $ALPHA / 2, $X + 1, $N - $X) ``` - `$ALPHA` is the significance, typically 0.05 - `$X` is the number of successful trials - `$N` is the total number of trial ## In Python ```python import numpy as np from scipy.stats import beta def clopper_pearson_interval(n_trials, successes, confint=0.95): quant = (1 - confint) / 2. low = beta.ppf(quant, n_trials, successes - n_trials + 1) high = beta.ppf(1 - quant, n_trials + 1, successes - n_trials) return (np.nan_to_num(low), np.where(np.isnan(high), 1, high)) ```