| 对假设检验使用中一个常见错误的澄清 |
| |
| 引用本文： | 仲晓波.对假设检验使用中一个常见错误的澄清[J].温州大学学报(社会科学版),2008(1):37-42. |
| |
| 作者姓名： | 仲晓波 |
| |
| 作者单位： | 温州大学教育科学学院,浙江温州325035 |
| |
| 摘 要： | 是否接受某个假设应该取决于这个假设成立的概率、当从实验获得样本观察值X之后，假设日成立的概率就是P（H／X）。所以，应该把P（H／X）≥e（e是一个足够大的概率常数）规定为接受假设目的条件并进而规定为确定日接受域的方法。这个方法对备择假设和零假设是同样适用的，据此可以证明：零假设的接受域不是备择假设接受域的余集。
|
| 关 键 词： | 假设检验 备择假设 零假设 |
Clarifying a Common Mistake in Using Hypothesis-test |
| |
| ZHONG Xiaobo.Clarifying a Common Mistake in Using Hypothesis-test[J].Journal of Wenzhou University Natural Science,2008(1):37-42. |
| |
| Authors: | ZHONG Xiaobo |
| |
| Institution: | ZHONG Xiaobo (School of Education, Wenzhou University, Wenzhou, China 325035) |
| |
| Abstract: | Whether we will accept a hypothesis should be determined by the probability that the hypothesis is right. When we obtain the observed value X of a sample from an experiment, the probability that hypothesis H is right is P（HIX）. Therefore, the qualification for receiving H and thereby the method for prescribing the receiving area for H should be P（HIX）≥e （e is a large enough probability constant）. The method is true not only for alternative hypothesis but also for null hypothesis, so it can be proved that the receiving area for null hypothesis is not the surplus set of the receiving area for alternative hypothesis. |
| |
| Keywords: | Hypothesis-test Alternative hypothesis Null hypothesis |
| 本文献已被 维普 等数据库收录！ |
