segreg.bootstrap.bca

bca(boot_sims, orig_sample_estimate, acceleration, significance, ties=False, respect_right=False)[source]

Computes BCa (bias-corrected and accelerated) confidence intervals for a single parameter.

References

This is described in numerous sources such as:

Davison, A.C., & Hinkley, D.V. (1997). “Bootstrap Methods and their

Application”. Cambridge University Press.

DiCiccio, T. J., & Efron, B. (1996). “Bootstrap confidence intervals.”

Statistical Science, 11 (3), 189-228

Parameters

  • boot_sims (scipy array shape (num_sims,)) –

  • orig_sample_estimate (float) – the estimate for the parameter from the original data sample

  • acceleration (float) – acceleration term for bca (can be zero)

  • significance (float) – The coverage of the confidence interval would be: 1 - significance. For example, a 95% confidence interval corresponds to a significance value of 0.05.

  • ties (bool) –

  • respect_right (bool) –

Returns

bca confidence interval – The endpoints of the confidence interval, left, right, respectively.

Return type

numpy array shape (2,)