bootstrap resampling

https://doi.org/10.1351/goldbook.11417

A procedure to evaluate the accuracy of the statistics of a model, such as the overall R2 or the contribution of particular properties, by systematically recomputing the statistics generated from many models developed using sample sets that contain the same number of observations as the original set, but for which certain observations are randomly omitted and other observations are included more than once.

See also: jackknifing
Source:
PAC, 2016, 88, 239. (Glossary of terms used in computational drug design, part II (IUPAC Recommendations 2015)) on page 242 [Terms] [Paper]