An Introduction to the BootstrapCRC Press, 1994/05/15 - 456 ページ An Introduction to the Bootstrap arms scientists and engineers as well as statisticians with the computational techniques they need to analyze and understand complicated data sets. The bootstrap is a computer-based method of statistical inference that answers statistical questions without formulas and gives a direct appreciation of variance, bias, coverage, and other probabilistic phenomena. This book presents an overview of the bootstrap and related methods for assessing statistical accuracy, concentrating on the ideas rather than their mathematical justification. Not just for beginners, the presentation starts off slowly, but builds in both scope and depth to ideas that are quite sophisticated. |
目次
| 1 | |
| 10 | |
3 Random samples and probabilities | 17 |
4 The empirical distribution function and the plugin principle | 31 |
5 Standard errors and estimated standard errors | 39 |
6 The bootstrap estimate of standard error | 45 |
some examples | 60 |
8 More complicated data structures | 86 |
17 Crossvalidation and other estimates of prediction error | 237 |
18 Adaptive estimation and calibration | 258 |
19 Assessing the error in bootstrap estimates | 271 |
20 A geometrical representation for the bootstrap and jackknife | 283 |
21 An overview of nonparametric and parametric inference | 296 |
22 Further topics in bootstrap confidence intervals | 321 |
23 Efficient bootstrap computations | 338 |
24 Approximate likelihoods | 358 |
9 Regression models | 105 |
10 Estimates of bias | 124 |
11 The jackknife | 141 |
12 Confidence intervals based on bootstrap tables | 153 |
13 Confidence intervals based on bootstrap percentiles | 168 |
14 Better bootstrap confidence intervals | 178 |
15 Permutation tests | 202 |
16 Hypothesis testing with the bootstrap | 220 |
25 Bootstrap bioequivalence | 372 |
26 Discussion and further topics | 392 |
software for bootstrap computations | 398 |
| 413 | |
Author index | 426 |
| 430 | |
他の版 - すべて表示
多く使われている語句
accuracy accurate algorithm analysis applied approach approximation assume average bias boot bootstrap estimate bootstrap replications bootstrap samples calculations called Chapter close coefficient components compute confidence intervals correct correlation curve data points data set defined Denote density derived described discussed distribution distribution F equal estimate of standard example expectation Figure formula function given gives histogram hormone hypothesis important indicate inference interest jackknife least left panel less likelihood limits linear matrix mean measures median method nonparametric normal notes Notice observed obtained original parameter percentile permutation points population probability problem procedure quantity random sample reasonable regression require right panel sample mean shown shows simple situation squared standard error standard normal statistic strap Suppose Table theory tion transformation true usually variable variance vector