dualbounds.bootstrap.multiplier_bootstrap¶
-
dualbounds.bootstrap.multiplier_bootstrap(samples: array, alpha: float, B: int =
1000, maxarrsize: int =10000000000, param: str ='max', verbose: int =False)[source]¶ Computes multiplier bootstrap lower confidence bounds.
Precisely, computes a lower confidence bound on \(\max(\mu_1, \dots, \mu_d)\), where \(\mu_i\) is the mean of
samples[i].- Parameters:¶
- samples : np.array¶
(n,d)-shaped array where samples[i] is i.i.d. with mean \(\mu_i\).
- alpha : float¶
Nominal error control level.
- B : int¶
Number of bootstrap replications
- maxarrsize : float¶
Maximum size of an array; used to save memory.
- param : str¶
If param=’max’, computes a lower confidence bound on \(\max(\mu_1, \dots, \mu_d)\).
Else, computes an upper confidence bound on \(\min(\mu_1, \dots, \mu_d)\),
- verbose : bool¶
If True, shows a progress bar. Only useful if
samplesis a very large matrix.
- Returns:¶
estimate (float) – Estimate of \(\max(\mu_1, \dots, \mu_d)\).
ci (float) – Lower confidence bound on \(\max(\mu_1, \dots, \mu_d)\).