作者bmka (偶素米虫)
站内Statistics
标题[讨论] What is p-value NOT
时间Sun Sep 4 12:54:35 2011
p-value是什麽应该是FAQ了,
来篇p-value不是什麽好了
- The p-value is not the probability that H0 is true.
- The p-value is not the probability that H0 is false.
- The p-value is not the probability that H1 is true.
- The p-value is not the probability that H1 is false.
- The p-value is not the probability that your results
are due to random chance.
- The p-value is not the probability that your results
are not due to random chance.
There is one other thing:
the p-value is NOT a measure of the size or importance of an effect.
A small p-value does not tell you by how much you are
rejecting H0 (the effect size), or whether that
rejection has any practical consequences.
引自
http://www.tc3.edu/instruct/sbrown/stat/pvalue.htm
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 173.73.120.121
1F：推 gsuper:一直以为P-value是第5项 假定P-value=0.01 09/04 16:52
2F：→ gsuper:难道不是在说在100次取样的 test statistic 中 09/04 16:53
3F：→ gsuper:会有一次随机发生如手上P=0.01的样本的 test statistic 吗 09/04 16:55
4F：→ gsuper:(假定不连续) 09/04 16:56
5F：推 west1996:p-value是一个conditional probability，所以重点是那个 09/04 18:03
6F：→ west1996:condition是什麽 09/04 18:03
7F：推 wertymin24:看不懂最後一段，如果全部都是否定的p-value到底是什麽 09/04 20:49
8F：→ bmka:wertymin24,贴这篇文章的主要目的正式要让大家思考p-value 09/04 22:19
9F：→ bmka:到底是什麽(可以吃吗),很多人会背定义,但是没有真正了解定义 09/04 22:21
10F：→ bmka:你认知的p-value是什麽? 09/04 22:21
11F：→ bmka:g大, 你可以从p-value判断这个研究资料是否是随机取样吗? 09/04 22:28
12F：→ bmka:反过来说,如果研究设计是随机取样,那不管观察值是什麽 09/04 22:33
13F：→ bmka:都是随机取样而来的(observed data are all due to random 09/04 22:34
14F：→ bmka:chance) 09/04 22:34
15F：推 wertymin24:我认知的定义比较操作性一点，以下文字取自wiki 09/05 01:31
16F：→ wertymin24:One often "rejects the null hypothesis" when the 09/05 01:31
17F：→ wertymin24:p-value is less than the significance level α 09/05 01:31
18F：→ wertymin24:, which is often 0.05 or 0.01. 09/05 01:32
19F：→ wertymin24: When the null hypothesis is rejected, the result i 09/05 01:32
20F：→ wertymin24: is said to be statistically significant. 09/05 01:32
21F：→ bmka:所以呢? 09/05 02:36
22F：→ bmka:跟最後一段有冲突吗? 09/05 02:44
23F：推 gsuper:P-value 我後来都用 false positive 的观点去想 09/05 03:13
24F：→ gsuper:好像用 AUC of ROC 会比直接看 P-value 来的有用 09/05 03:17
25F：→ gsuper:因为 type I error 只讲了一半的事情 09/05 03:17
26F：推 wertymin24:bmka大~我知道没有冲突啦~我只是回应你，你问的我认知 09/05 10:49
27F：→ wertymin24:的pvalue是什麽 09/05 10:50
28F：推 tew:应该说 不要太执着於做出有很多星星的文章 09/08 00:36
29F：→ tew:而是给予目前这个结果的合理解释或者说法 09/08 00:36
30F：→ bmka:是的,贴这篇正是为了回应上一篇文章 09/08 01:52
31F：推 goshfju:一颗星 两颗星 三颗星 XD 09/08 19:29