a***e 发帖数: 1627 | 1 我用的是logistic regression,得到的odds ratio的CI 是0.5 到 1.3 包括1,就是这
两个variable not significant associated , 可是p value < 0.05
请问各位可能吗? 我应该怎么解释呢
谢谢 |
N******n 发帖数: 3003 | 2 理解的对吗?
odd ratio=1--->significant associated?
不过,按 p value解释就行了。
【在 a***e 的大作中提到】 : 我用的是logistic regression,得到的odds ratio的CI 是0.5 到 1.3 包括1,就是这 : 两个variable not significant associated , 可是p value < 0.05 : 请问各位可能吗? 我应该怎么解释呢 : 谢谢
|
s*r 发帖数: 2757 | 3 are you looking at the coefficient estimation or OR |
n****e 发帖数: 226 | 4 mostly like that's the CI for for the regression coefficients.
【在 s*r 的大作中提到】 : are you looking at the coefficient estimation or OR
|
n****e 发帖数: 226 | 5 Are you using SAS? It will be helpful if you can post the screenshot of the
part of the output you were describing.
【在 a***e 的大作中提到】 : 我用的是logistic regression,得到的odds ratio的CI 是0.5 到 1.3 包括1,就是这 : 两个variable not significant associated , 可是p value < 0.05 : 请问各位可能吗? 我应该怎么解释呢 : 谢谢
|
a***e 发帖数: 1627 | 6 谢谢各位大牛,我想我找到原因了。。
The answer is that SAS uses effect coding for the coefficients, but uses
dummy variable coding when calculating the odds ratios. Because they are not
making the same comparisons, it is possible for the coefficients in the
table of estimates to be non-significant while the confidence interval
around the odds ratios does not include one (or vice versa). |