Consistency of the bootstrap for the ransformed two-sample t-test |
| |
Authors: | Hanfeng chen Wei-Yin Loh |
| |
Institution: | 1. Department of Mathematics and Statistics , Bowling Green State University , Bowling Green, OH, 43403;2. Department of Statistics , University of Wisconsin-Madison , Madison, WI, 53706 |
| |
Abstract: | A method of bootstrapping the two-sample t-test after a Box-Cox transformation is proposed. The procedure is shown to be consistent and asymptotically as efficient as the non-bootstrapped Box-Cox t-test. Because the bootstrap samples are drawn without the assumption of the same distributional shapes,the procedure may be more robust against violation of this assumption. Simulation results support this conjecture. |
| |
Keywords: | Asympotic relative efficiency Box-Cox transformation |
|
|