![]() |
|
|
Monday, March 25, 2002 4:30 PM in MATH 215 Mr. Kristofer Jennings Stanford University will speak on A New Approach to Bias Reduction Using the Iterated Bootstrap Abstract Algorithms based on the iterated bootstrap are known to have excellent convergence properties for many statistical problems. However, the practical value of these methods is diminished by the large computational costs that are incurred after even a few iterations. We propose, in the context of bootstrap bias reduction, an algorithm which does not suffer from these limitations. This method, found by taking the limit of a method proposed by Hall and Martin (Biometrika, 1988), compares favorably on both theoretical and practical grounds to previously proposed methods of bias reduction. In addition, our algorithm can be modified to estimate higher level moments of bias-corrected statistics. We will briefly discuss how these methods can be used in several applications. |
|
Seminars and Events | Research | Consulting | Career Resources Related Programs and Links | Site Index | Site Search |
|
Last Update: Mar 22, 2002 Please send comments and suggestions to the Webmaster. |