| 假设检验中无差别区域问题的讨论 |
| |
| 引用本文： | 王雅玲.假设检验中无差别区域问题的讨论[J].北京工商大学学报(自然科学版),2006,24(3):63-65. |
| |
| 作者姓名： | 王雅玲 |
| |
| 作者单位： | 北京工商大学,基础部,北京,100037 |
| |
| 摘 要： | 理论上,假设检验会出现两类决策错误:“弃真”和“取伪”.在实际应用中,可能出现这样一种特殊情况:真值与假设值的差异微小到可以视为二者相等,即存在着无差别区域.对于无差别区域内不等于假设值的真值,只要样本容量足够大,显著性假设检验几乎以概率1拒绝原假设,这显然不符合实际应用的需要.本文对实际应用中假设检验的检验目标进行了修正,限定样本容量的取值范围,使假设检验的决策结果更为客观合理.
|
| 关 键 词： | 假设检验 无差别区域 检验目标 样本容量 |
| 文章编号： | 1671-1513（2006）03-0063-03 |
| 收稿时间： | 2005-12-01 |
| 修稿时间： | 2005年12月1日 |
DISCUSSION ABOUT INDIFFERENCE RANGE IN HYPOTHESIS TESTING |
| |
| WANG Ya-ling.DISCUSSION ABOUT INDIFFERENCE RANGE IN HYPOTHESIS TESTING[J].Journal of Beijing Technology and Business University:Natural Science Edition,2006,24(3):63-65. |
| |
| Authors: | WANG Ya-ling |
| |
| Institution: | Department of Basic Studies, Beijing Technology and Business University, Beijing 100037, China |
| |
| Abstract: | On the theoretical grounds,there are two kinds of error in testing of hypothesis: abandoning the true and accepting the false.In practice,there is an indifference range,that is the difference between real value and the postulated value is tiny enough.When the sample size is large enough,the approximate probability of "rejecting H_0" is 1 no matter how miniature the dissimilarity is.This paper modifies the objection of the test,and suggests that the sample size should be limited in a proper range. |
| |
| Keywords: | hypothesis-testing indifference range test object sample size |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
