āļ„āļđāđˆāļĄāļ·āļ­āļ—āļēāļ‡āđ€āļ—āļ„āļ™āļīāļ„

āļāļēāļĢāļŠāļļāđˆāļĄāļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡ Bootstrap

Bootstrap resampling estimates uncertainty by repeatedly drawing new samples, with replacement, from the data you observed and recalculating a statistic.

āļŸāļąāļ‡āļ„āļģāđāļ™āļ°āļ™āļģāļ™āļĩāđ‰āļšāļĢāļĢāļĒāļēāļĒāđ‚āļ”āļĒ AI · ~3 min

āļšāļ™āļŦāļ™āđ‰āļēāļ™āļĩāđ‰āļ­āđˆāļēāļ™ 3 āļ™āļēāļ—āļĩ
  1. āļ āļēāļžāļĢāļ§āļĄ
  2. āđ€āļˆāļēāļ°āļĨāļķāļ
  3. āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļˆāļĢāļīāļ‡āđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡
  4. The Future of Bootstrap Resampling
  5. āļāļēāļĢāļ™āļģāđ„āļ›āļ›āļāļīāļšāļąāļ•āļī
  6. āļŠāļģāļĢāļ§āļˆāļ•āđˆāļ­āđ„āļ›
  7. āļ„āļģāļ–āļēāļĄāļ—āļĩāđˆāļžāļšāļšāđˆāļ­āļĒ

āļ āļēāļžāļĢāļ§āļĄ

It can help describe how a mean or model-evaluation metric varies, provided the resampling design matches how the observations are related.

āđ€āļˆāļēāļ°āļĨāļķāļ

A statistic calculated from one dataset is only an estimate. Another sample from the same population could produce a different mean, correlation or evaluation score. The bootstrap approximates aspects of that sampling variation using the observations already available. In the ordinary nonparametric bootstrap for independent observations, draw a sample of the original size with replacement. Each draw can select any original observation again, so some observations appear more than once and others are omitted. Calculate the statistic on that sample. Repeat the process many times to produce a distribution of bootstrap statistics. For an arithmetic illustration, the values 2, 4 and 9 have a mean of five. A possible resample is 2, 2 and 9, whose mean is about 4.33. One resample does not establish an uncertainty interval. The variation across many appropriately constructed resamples is what makes the procedure useful. A percentile interval takes endpoints from percentiles of the bootstrap distribution. Other methods, including the bias-corrected and accelerated method supported by SciPy, adjust the construction differently. The chosen method and its assumptions matter, particularly for small samples or difficult statistics. For paired data, preserve the pairing. When comparing model predictions on the same cases, resample each case with its outcome and both predictions. Breaking those relationships changes the question being evaluated. The bootstrap cannot create evidence about people or conditions missing from the original sample. It also does not automatically correct selection bias or dependence between observations. Repeated measurements may require resampling groups; time series may require a suitable block method. Choose the resampling unit to reflect the data-generating process before interpreting the apparent precision.

āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļˆāļĢāļīāļ‡āđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡

Starting from the illustrative values 2, 4 and 9, one bootstrap sample might be 2, 2 and 9. It has the same size as the original sample, includes a repeated observation and has a mean of 13 divided by three.

To compare two models on the same test cases, an analyst resamples case identifiers and carries both models' predictions and the true outcome together. Each resample yields a difference in their scores.

A study has several records per participant. The analyst considers resampling whole participants rather than treating every record as independent.

A team uses scipy.stats.bootstrap to estimate uncertainty in a statistic. It records the interval method and random seed and checks whether the resulting interval is stable enough for its intended use.

The Future of Bootstrap Resampling

Evaluation reports could become more useful by recording the resampling unit, interval method and scope of uncertainty alongside the resulting bounds. A reader should be able to tell whether an interval describes a fixed model on new cases or a process that includes refitting. Teams can also preserve resampled indices and software versions when reproducibility matters. The next improvement is often a better evaluation sample rather than more bootstrap repetitions. Understanding which sources of uncertainty are included makes the interval more actionable than presenting narrow bounds without their assumptions.

āļāļēāļĢāļ™āļģāđ„āļ›āļ›āļāļīāļšāļąāļ•āļī

āļ—āļģāđ„āļĄāļĄāļąāļ™āļ–āļķāļ‡āļŠāļģāļ„āļąāļ

  • āļ•āđ‰āļ™āļ—āļļāļ™āđāļĨāļ°āļ‡āļšāļ›āļĢāļ°āļĄāļēāļ“. āļāļēāļĢāļ•āļąāļ”āļŠāļīāļ™āđƒāļˆāļ”āđ‰āļēāļ™āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļ‚āļąāļšāđ€āļ„āļĨāļ·āđˆāļ­āļ™āļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļžāđāļĨāļ°āļ•āđ‰āļ™āļ—āļļāļ™āļāļēāļĢāļ”āļģāđ€āļ™āļīāļ™āļ‡āļēāļ™āđ€āļ›āđ‡āļ™āđ€āļ§āļĨāļēāļŦāļĨāļēāļĒāļ›āļĩ
  • āļāļēāļĢāļ•āļąāļ”āļŠāļīāļ™āđƒāļˆāļ—āļĩāđˆāļŠāļąāļ”āđ€āļˆāļ™āļĒāļīāđˆāļ‡āļ‚āļķāđ‰āļ™. āļāļēāļĢāļĻāļķāļāļĐāļēāļ”āđ‰āļēāļ™āđ€āļ—āļ„āļ™āļīāļ„āļŠāđˆāļ§āļĒāđƒāļŦāđ‰āļ—āļĩāļĄāđ€āļĨāļ·āļ­āļāļāļĨāļļāđˆāļĄāļ—āļĩāđˆāđ€āļŦāļĄāļēāļ°āļŠāļĄ āđ„āļĄāđˆāđƒāļŠāđˆāđāļ„āđˆāļāļĨāļļāđˆāļĄāđƒāļŦāļĄāđˆāļĨāđˆāļēāļŠāļļāļ”
  • āļāļēāļĢāļ„āļ§āļšāļ„āļļāļĄāļ„āļļāļ“āļ āļēāļž. āļ•āļąāļ§āđ€āļĨāļ·āļ­āļāļ—āļēāļ‡āļ§āļīāļĻāļ§āļāļĢāļĢāļĄāļ—āļĩāđˆāļ”āļĩāļāļ§āđˆāļēāļˆāļ°āļŠāđˆāļ§āļĒāļĨāļ”āđ€āļŦāļ•āļļāļāļēāļĢāļ“āđŒāļ”āđ‰āļēāļ™āļ„āļ§āļēāļĄāļ™āđˆāļēāđ€āļŠāļ·āđˆāļ­āļ–āļ·āļ­āđƒāļ™āļāļēāļĢāļœāļĨāļīāļ•

āļĢāļ°āļ§āļąāļ‡

  • āļāļēāļĢāđ€āļžāļīāđˆāļĄāļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļžāđ€āļāļ“āļ‘āđŒāļĄāļēāļ•āļĢāļāļēāļ™āļŦāļ™āļķāđˆāļ‡āļĢāļēāļĒāļāļēāļĢāļŠāļēāļĄāļēāļĢāļ–āļ‹āđˆāļ­āļ™āļˆāļļāļ”āļ­āđˆāļ­āļ™āļ‚āļ­āļ‡āļĢāļ°āļšāļšāđƒāļ™āļ§āļ‡āļāļ§āđ‰āļēāļ‡āđ„āļ”āđ‰
  • āļ•āđ‰āļ™āļ—āļļāļ™āđ‚āļ„āļĢāļ‡āļŠāļĢāđ‰āļēāļ‡āļžāļ·āđ‰āļ™āļāļēāļ™āđāļĨāļ°āļāļēāļĢāļšāļģāļĢāļļāļ‡āļĢāļąāļāļĐāļēāļĄāļąāļāļ–āļđāļāļ›āļĢāļ°āđ€āļĄāļīāļ™āļ•āđˆāļģāđ„āļ›
  • āļŠāđˆāļ­āļ‡āļ§āđˆāļēāļ‡āļ”āđ‰āļēāļ™āļ„āļ§āļēāļĄāļ›āļĨāļ­āļ”āļ āļąāļĒāđāļĨāļ°āļ„āļ§āļēāļĄāļŠāļēāļĄāļēāļĢāļ–āđƒāļ™āļāļēāļĢāļŠāļąāļ‡āđ€āļāļ•āļŠāļēāļĄāļēāļĢāļ–āđ€āļžāļīāđˆāļĄāļ‚āļķāđ‰āļ™āđ„āļ”āđ‰āđ€āļĄāļ·āđˆāļ­āļĢāļ°āļšāļšāļĄāļĩāļ„āļ§āļēāļĄāļ‹āļąāļšāļ‹āđ‰āļ­āļ™āļĄāļēāļāļ‚āļķāđ‰āļ™

āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āļ•āđˆāļ­āđ„āļ›

  1. āļāļģāļŦāļ™āļ”āđ€āļ›āđ‰āļēāļŦāļĄāļēāļĒāđ€āļ§āļĨāļēāđāļāļ‡ āļ„āļļāļ“āļ āļēāļž āđāļĨāļ°āļ•āđ‰āļ™āļ—āļļāļ™āļāđˆāļ­āļ™āļ™āļģāđ„āļ›āđƒāļŠāđ‰āļ‡āļēāļ™
  2. āđ€āļāļ“āļ‘āđŒāļĄāļēāļ•āļĢāļāļēāļ™āļ āļēāļĒāđƒāļ•āđ‰āļŠāļ āļēāļ§āļ°āđ‚āļŦāļĨāļ”āđāļĨāļ°āļ‚āđ‰āļ­āļĄāļđāļĨāļˆāļĢāļīāļ‡
  3. āļāļēāļĢāļ•āļĢāļ§āļˆāļŠāļ­āļšāđ€āļ„āļĢāļ·āđˆāļ­āļ‡āļĄāļ·āļ­āđ€āļžāļ·āđˆāļ­āļŦāļēāļ‚āđ‰āļ­āļœāļīāļ”āļžāļĨāļēāļ” āļāļēāļĢāđ€āļšāļĩāđˆāļĒāļ‡āđ€āļšāļ™ āđāļĨāļ°āļœāļĨāļāļĢāļ°āļ—āļšāļ•āđˆāļ­āļœāļđāđ‰āđƒāļŠāđ‰
  4. āđ€āļ•āļĢāļĩāļĒāļĄāđ€āļŠāđ‰āļ™āļ—āļēāļ‡āļāļēāļĢāļĒāđ‰āļ­āļ™āļāļĨāļąāļšāđāļĨāļ°āļāļēāļĢāļ•āļ­āļšāļŠāļ™āļ­āļ‡āļ•āđˆāļ­āđ€āļŦāļ•āļļāļāļēāļĢāļ“āđŒāļāđˆāļ­āļ™āļ›āļĢāļąāļšāļ‚āļ™āļēāļ”

āļŠāļģāļĢāļ§āļˆāļ•āđˆāļ­āđ„āļ›

āļˆāļ”āļŦāļĄāļēāļĒāļ‚āđˆāļēāļ§āļŸāļĢāļĩ

āļĢāļąāļšāļŠāļĢāļļāļ› AI āļĢāļēāļĒāļ§āļąāļ™

āđ€āļĢāļ·āđˆāļ­āļ‡āļĢāļēāļ§ AI āļ—āļĩāđˆāļ•āļĢāļ§āļˆāļŠāļ­āļšāđāļĨāđ‰āļ§ 3 āđ€āļĢāļ·āđˆāļ­āļ‡āļ—āļļāļāļ§āļąāļ™āļ—āļģāļ‡āļēāļ™ āđ€āļŠāđ‰āļē, āđ€āļ‚āļĩāļĒāļ™āđ€āļ›āđ‡āļ™āļ āļēāļĐāļēāļ­āļąāļ‡āļāļĪāļĐāļ˜āļĢāļĢāļĄāļ”āļē āļŸāļĢāļĩāļ•āļĨāļ­āļ”āđ„āļ› āđ„āļĄāđˆāļĄāļĩāđ‚āļ†āļĐāļ“āļē

āļ­āļĩāđ€āļĄāļĨāļŦāļ™āļķāđˆāļ‡āļ‰āļšāļąāļšāļ—āļļāļāļ§āļąāļ™āļ—āļģāļ‡āļēāļ™ āļĒāļāđ€āļĨāļīāļāļāļēāļĢāļŠāļĄāļąāļ„āļĢāđƒāļ™āļ„āļĨāļīāļāđ€āļ”āļĩāļĒāļ§ āđ€āļĢāļēāđ„āļĄāđˆāđ€āļ„āļĒāļ‚āļēāļĒāļŦāļĢāļ·āļ­āđāļŠāļĢāđŒāļ—āļĩāđˆāļ­āļĒāļđāđˆāļ­āļĩāđ€āļĄāļĨāļ‚āļ­āļ‡āļ„āļļāļ“

āļ—āļ”āļŠāļ­āļšāļ•āļąāļ§āđ€āļ­āļ‡

Take the Bootstrap Resampling quiz

āļ‚āđ‰āļ­āđ€āļŠāļ™āļ­āđāļ™āļ°āļ—āļąāļ™āļ—āļĩāļŠāļģāļŦāļĢāļąāļšāļ—āļļāļāļ„āļģāļ•āļ­āļš āđāļĨāļ°āđƒāļšāļĢāļąāļšāļĢāļ­āļ‡āļ—āļĩāđˆāļŠāļēāļĄāļēāļĢāļ–āđāļŠāļĢāđŒāđ„āļ”āđ‰āļžāļĢāđ‰āļ­āļĄ ID āļ—āļĩāđˆāļ•āļĢāļ§āļˆāļŠāļ­āļšāđ„āļ”āđ‰āđ€āļĄāļ·āđˆāļ­āļ„āļļāļ“āļœāđˆāļēāļ™āļŦāļĨāļąāļāļŠāļđāļ•āļĢ

āđ€āļĢāļīāđˆāļĄāđāļšāļšāļ—āļ”āļŠāļ­āļš

āļŠāļ™āļąāļšāļŠāļ™āļļāļ™āļāļēāļĢāļĻāļķāļāļĐāļē AI āļŸāļĢāļĩ AI Understanding āđ€āļ›āđ‡āļ™āļ­āļ‡āļ„āđŒāļāļĢāđ„āļĄāđˆāđāļŠāļ§āļ‡āļŦāļēāļœāļĨāļāļģāđ„āļĢ 501(c)(3) — āđ„āļĄāđˆāļĄāļĩāđ‚āļ†āļĐāļ“āļē āđ„āļĄāđˆāļĄāļĩāļāļģāđāļžāļ‡āđ€āļ‡āļīāļ™, āļ•āļĨāļ­āļ”āđ„āļ› āļšāļĢāļīāļˆāļēāļ„

āļ„āļģāļ–āļēāļĄāļ—āļĩāđˆāļžāļšāļšāđˆāļ­āļĒ

What is Bootstrap Resampling?

Bootstrap resampling estimates uncertainty by repeatedly drawing new samples, with replacement, from the data you observed and recalculating a statistic. It can help describe how a mean or model-evaluation metric varies, provided the resampling design matches how the observations are related.

āļāļĢāļ°āļšāļ§āļ™āļāļēāļĢāļŠāļļāđˆāļĄāļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āđƒāļ”āļ—āļĩāđˆāļ—āļģāļ•āļēāļĄāļāļŽ bootstrap āļ›āļāļ•āļīāļŠāļģāļŦāļĢāļąāļšāļŠāļąāļ‡āđ€āļāļ•āļāļēāļĢāļ“āđŒāļ•āđ‰āļ™āļ‰āļšāļąāļš 2, 4 āđāļĨāļ° 9?

A bootstrap sample has the original size and is drawn with replacement, allowing repeated observations.

āļ„āđˆāļēāđ€āļ‰āļĨāļĩāđˆāļĒāđƒāļ”āđ€āļ›āđ‡āļ™āļŠāđˆāļ§āļ™āļŦāļ™āļķāđˆāļ‡āļ‚āļ­āļ‡āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡ bootstrap āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āđ€āļŠāļīāļ‡āļ­āļ˜āļīāļšāļēāļĒ 2, 2 āđāļĨāļ° 9?

The three resampled values sum to 13, so their mean is 13 divided by three, approximately 4.33.

āđ€āļĄāļ·āđˆāļ­āđ€āļ›āļĢāļĩāļĒāļšāđ€āļ—āļĩāļĒāļšāđ‚āļĄāđ€āļ”āļĨāļŠāļ­āļ‡āļ•āļąāļ§āļšāļ™āļāļĢāļ“āļĩāļ—āļ”āļŠāļ­āļšāđ€āļ”āļĩāļĒāļ§āļāļąāļ™ āļŠāļīāđˆāļ‡āđƒāļ”āļ•āđ‰āļ­āļ‡āļ­āļĒāļđāđˆāļĢāđˆāļ§āļĄāļāļąāļ™āđƒāļ™āđāļ•āđˆāļĨāļ°āļŦāļ™āđˆāļ§āļĒāļ—āļĩāđˆāļ—āļģāļāļēāļĢāļŠāļļāđˆāļĄāđƒāļŦāļĄāđˆ?

Preserving the case-level pairing allows the resampled score difference to compare predictions for the same observations.

āļˆāļļāļ”āļŠāļīāđ‰āļ™āļŠāļļāļ”āđƒāļ”āļšāđ‰āļēāļ‡āļ—āļĩāđˆāļāļģāļŦāļ™āļ”āļŠāđˆāļ§āļ‡ bootstrap āđ€āļ›āļ­āļĢāđŒāđ€āļ‹āđ‡āļ™āđ„āļ—āļĨāđŒāļŠāļ­āļ‡āļ”āđ‰āļēāļ™ 95% āļ—āļĩāđˆāļ­āļ˜āļīāļšāļēāļĒ?

The percentile method uses quantiles of the resampled statistics, with 2.5% left in each tail for this interval.

āļāļēāļĢāđ€āļžāļīāđˆāļĄāļˆāļģāļ™āļ§āļ™āļāļēāļĢāļŠāļļāđˆāļĄ bootstrap āļˆāļ°āļĨāļ”āļ­āļ°āđ„āļĢāđ€āļ›āđ‡āļ™āļŦāļĨāļąāļ?

More repetitions make the simulation more stable but do not provide new independent observations or repair sampling problems.

āđ€āļĢāļĩāļĒāļ™āļĢāļđāđ‰āļ•āđˆāļ­āđ„āļ›

āļ„āļģāđāļ™āļ°āļ™āļģāļ—āļĩāđˆāđ€āļāļĩāđˆāļĒāļ§āļ‚āđ‰āļ­āļ‡

āļ„āļģāđāļ™āļ°āļ™āļģāđ€āļžāļīāđˆāļĄāđ€āļ•āļīāļĄāļ—āļĩāđˆāđ€āļĨāļ·āļ­āļāļŠāļģāļŦāļĢāļąāļšāļŦāļąāļ§āļ‚āđ‰āļ­āļ™āļĩāđ‰

āļ•āđˆāļ­āđ„āļ›āļ„āļģāđāļ™āļ°āļ™āļģāļ•āđˆāļ­āđ„āļ›

āļ„āļ§āļēāļĄāđ„āļĄāđˆāļŠāļĄāļ”āļļāļĨāļ‚āļ­āļ‡āļ„āļĨāļēāļŠāđāļĨāļ°āļāļēāļĢāļŠāļļāđˆāļĄāļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āđƒāļŦāļĄāđˆ

āđ€āļ—āļ„āļ™āļīāļ„

āļĢāļąāļšāđƒāļšāļĢāļąāļšāļĢāļ­āļ‡ AI āļŸāļĢāļĩāļŦāļĨāļąāļāļŠāļđāļ•āļĢāđāļĨāļ°āļāļēāļĢāļŠāļ­āļšāļŠāļąāđ‰āļ™ āđ† āļŸāļĢāļĩ āđ„āļĄāđˆāļĄāļĩāļ„āđˆāļēāđƒāļŠāđ‰āļˆāđˆāļēāļĒ āđ„āļĄāđˆāļĄāļĩāļšāļąāļ•āļĢāđ€āļ„āļĢāļ”āļīāļ• āļ›āļĢāļ°āļĄāļēāļ“ 2.5 āļŠāļąāđˆāļ§āđ‚āļĄāļ‡āđ€āļĢāļīāđˆāļĄāļ•āđ‰āļ™āļŸāļĢāļĩ →