Main Content

Resampling Techniques

Resample data set using bootstrap, jackknife, and cross validation

Use resampling techniques to estimate descriptive statistics and confidence intervals from sample data when parametric test assumptions are not met, or for small samples from non-normal distributions. Bootstrap methods choose random samples with replacement from the sample data to estimate confidence intervals for parameters of interest. Jackknife systematically recalculates the parameter of interest using a subset of the sample data, leaving one observation out of the subset each time (leave-one-out resampling). From these calculations, it estimates the parameter of interest for the entire data sample. If you have a Parallel Computing Toolbox™ license, you can use parallel computing to speed up resampling calculations.


bootciBootstrap confidence interval
bootstrpBootstrap sampling
crossvalEstimate loss using cross-validation
datasampleRandomly sample from data, with or without replacement
jackknifeJackknife sampling
randsampleRandom sample