Bootstrapping is a form of empirical statistics. It creates lots of new datasets by taking subsamples of the initial data (perhaps gathered in an experiment). The value of a statistical measure is calculated for every subsample, for example the average divided by the standard deviation. The value of the same statistic on the origional data is compared with the set of values to determine its p value. Bootstrapping does not require any prior knowledge of the distribution of the data.
Used in Chap. 13: page 151
Also used in hcistats2e: Chap. 10: page 111
Used in glossary entries: empirical statistics, subsample