Bootstrap Tests: How Many Bootstraps?. Davidson, R. & MacKinnon, J. G. 19(1):55–68.
Bootstrap Tests: How Many Bootstraps? [link]Paper  doi  abstract   bibtex   
In practice, bootstrap tests must use a finite number of bootstrap samples. This means that the outcome of the test will depend on the sequence of random numbers used to generate the bootstrap samples, and it necessarily results in some loss of power. We examine the extent of this power loss and propose a simple pretest procedure for choosing the number of bootstrap samples so as to minimize experimental randomness. Simulation experiments suggest that this procedure will work very well in practice.
@article{davidsonBootstrapTestsHow2000,
  title = {Bootstrap Tests: How Many Bootstraps?},
  author = {Davidson, Russell and MacKinnon, James G.},
  date = {2000-01},
  journaltitle = {Econometric Reviews},
  volume = {19},
  pages = {55--68},
  issn = {1532-4168},
  doi = {10.1080/07474930008800459},
  url = {https://doi.org/10.1080/07474930008800459},
  abstract = {In practice, bootstrap tests must use a finite number of bootstrap samples. This means that the outcome of the test will depend on the sequence of random numbers used to generate the bootstrap samples, and it necessarily results in some loss of power. We examine the extent of this power loss and propose a simple pretest procedure for choosing the number of bootstrap samples so as to minimize experimental randomness. Simulation experiments suggest that this procedure will work very well in practice.},
  keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-8045277,bootstrap,communicating-uncertainty,resampling,statistics,uncertainty},
  number = {1}
}

Downloads: 0