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.
|Bootstrap confidence interval|
|Estimate loss using cross-validation|
|Randomly sample from data, with or without replacement|
- Resampling Statistics
Use bootstrap and jackknife methods to measure the uncertainty in the estimated parameters and statistics.
- Quick Start Parallel Computing for Statistics and Machine Learning Toolbox
Get started with parallel statistical computing.
- Implement Jackknife Using Parallel Computing
Speed up the jackknife using parallel computing.
- Implement Cross-Validation Using Parallel Computing
Speed up cross-validation using parallel computing.
- Implement Bootstrap Using Parallel Computing
Speed up the bootstrap using parallel computing.