[求助]各位大虾帮我解答一下啊！

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

做f检验 双样本方差分析时，显著性水平为0,05的情况下， p<o.o5 , F> F临界值。这样应该是有统计学意义的吧？

但是如果 p<o.o5 , F< F临界值, 这样算什么啊？

好心的帮我解答一下啊。关系我毕业大事啊。先谢了！

[此贴子已经被作者于2006-4-8 21:49:41编辑过]

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：方差分析 F检验 临界值 统计学 求助 解答 大虾

怎么没人理我哦？

If you know what p-value is, you will not ask this question!

如果  p&lt;o.o5 , F&lt; F临界值, 这样的结果只有一种解释,即F临界值是根据更小的显著性水平来查的,例如概率值为0.04,小于0.05,但你根据0.01的显著性水平来查F临界值,就会出现上述的结果.

这年头咋都这样

Generally, For F test, it's upper tail test. It means, Reject H0 if F>F(a,df1,df2). and also you can use P-value to decide your decision. If P-value >a, fail to reject H0, otherwise, reject H0.

I am confused by the results you got b/c you got different decisions if you use F value and P-value methods...

Is there something wrong with your program or data....? don't know.

May I know which software you use? Eviews, STATA, or Gauss?

I am not clear whether your p-value refers to your F-statistic. If so, the second case will not happen. Again, I need to know whether your p-value refers to the joint significance test associated with your F-statistic.

Thank you.

At first, you need to know the purpose of F-test in your case, i.e what's the null hypothesis H0 and What's the alternative hypothesis H1.

Your results (F>Fc or p<0.05) show that the test statistic is singnificant in 5% level. I.e the H0 is rejected in this case.

Under same singnificant level such as 5%, the results F<Fc and p<0.05 are impossible.

Use your pencil draw a pdf of some F, shade the tail area 5% at the upper side or on both sides... Then figure out where is the p where is the CV. It has nothing to do with software, any, at this stage.