简体   繁体   English

如何在带有Scipy的两个尾部T检验之间进行选择?

[英]How to choose between a two tailed and one tailed T-test with scipy?

Scipy website seems to be down again :( Scipy网站似乎再次掉线了:(

I am conducting a paired t test. 我正在进行配对t检验。 But I am not sure how to choose between two-tailed and one-tailed (I need to use two-tailed). 但是我不确定如何在两尾和一尾之间进行选择(我需要使用两尾)。 And also the ttest_reul only return t and p values. 而且ttest_reul只返回t和p值。 Anyway to find out degrees of freedom? 反正找出自由度? Many thanks 非常感谢

from scipy import stats
t_val_Input, p_val_Input = stats.ttest_rel(c1,c2)

From the docstring of ttest_rel : ttest_rel的文档字符串:

ttest_rel(a, b, axis=0, nan_policy='propagate') ttest_rel(a,b,轴= 0,nan_policy ='传播')

Calculates the T-test on TWO RELATED samples of scores, a and b. 在两个相关的分数a和b样本上计算T检验。

This is a two-sided test for the null hypothesis that 2 related or repeated samples have identical average (expected) values. 这是对2个相关样本或重复样本具有相同的平均(预期)值的原假设的双向检验。

"Two-sided" means two-tailed. “双面”是指两尾。

The degrees of freedom is n - 1 , where n is the number of pairs (ie len(a) or len(b) ). 自由度是n - 1 ,其中n是对的数量(即len(a)len(b) )。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM