论文部分内容阅读
问:统计学里如何选择检验水准(何时选择P<0.01或选择P<0.05为差异有统计学意义)?答:一般选择P<0.05为差异有统计学意义,称之为检验水准。具体来说,假如在无效假设(比如两组均数比较为差异无统计学意义,或相关性分析为因变量与应变量无关)成立的情况下,获得某个检验值(如t值,χ~2值)计算出该假设成立概率,如果P<0.05,或者P<0.01,我们有理由拒绝无效假设,也就是说,两组均数之间差异有统计学意义,或者
Q: How to choose the test level in statistics (when to choose P <0.01 or select P <0.05 for the difference was statistically significant)? A: The general choice of P <0.05 for the difference was statistically significant, called the test level. Specifically, if the null hypothesis (for example, no significant difference between the two groups, or the correlation analysis is independent of the dependent variable), a test value (such as t value, χ ~ 2) to calculate the probability of this hypothesis, if P <0.05, or P <0.01, we have reason to reject the null hypothesis, that is, the difference between the two groups was statistically significant, or