Use this tag for questions related to a statistical test or metric that relies on random sampling with replacement.
In statistics, bootstrapping is any test or metric that relies on random sampling with replacement. Bootstrapping allows one to—
- assign measures of accuracy (e.g., bias, variance, confidence intervals, prediction error) to sample estimates,
- estimate the sampling distribution of almost any statistic,
- construct hypothesis tests, and
- make statistical inferences based on the assumption of a parametric model if that assumption is in doubt, or if parametric inference is impossible or requires complicated formulas for the calculation of standard errors.
The basic idea of bootstrapping is that inference about a population from sample data (sample → population) can be modelled by resampling the sample data and performing inference about a sample from resampled data (resampled → sample). As the population is unknown, the true error in a sample statistic against its population value is unknown. In bootstrap resamples, the "population" is in fact the sample, and this is known; hence the quality of inference of the "true" sample from resampled data (resampled → sample) is measurable.
