A Short Prehistory of the Bootstrap

The contemporary development of methods, from the time of Efron's early articles to the day, is well documented and widely appreciated. Likewise, relationship of bootstrap techniques to certain early work on testing, the jackknife and cross-validation is well. Less known, however, are the connections of the bootstrap to on survey sampling for spatial data in the first half of the century or to work from the 1940s to the 1970s on subsampling resampling. In a selective way, some of these linkages will be explored, emphasis to developments with which the community tends to be less familiar. Particular will be paid to the work of P. C. Mahalanobis, whose development in 1930s and 1940s of moving-block sampling methods for spatial has a range of interesting features, and to contributions of scientists who, during the next 40 years, developed-sampling, subsampling and resampling methods.