我使用 or_glm() 来计算优势比,使用这个可重现的示例:
library(oddsratio)
or_glm(data = data_glm,
model = glm(admit ~ gre + gpa + rank,
data = data_glm,
family = "binomial"),
incr = list(gre = 1, gpa = 1, rank = 1))
我有两个问题:
- 如何提取每个优势比的 p 值?
- 如何获得针对“gpa”和“rank”调整后的“gre”优势比?
最佳答案
我会尝试如下:
library(oddsratio)
library(mfx)
model = glm(admit ~ gre + gpa + rank,
data = data_glm,
family = "binomial")
logitor(admit ~ gre + gpa + rank,data=data_glm)
Call:
logitor(formula = admit ~ gre + gpa + rank, data = data_glm)
Odds Ratio:
OddsRatio Std. Err. z P>|z|
gre 1.0022670 0.0010965 2.0699 0.0384651 *
gpa 2.2345448 0.7414651 2.4231 0.0153879 *
rank2 0.5089310 0.1610714 -2.1342 0.0328288 *
rank3 0.2617923 0.0903986 -3.8812 0.0001039 ***
rank4 0.2119375 0.0885542 -3.7131 0.0002047 ***
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
exp(coef(model))
(Intercept) gre gpa rank2
0.0185001 1.0022670 2.2345448 0.5089310
rank3 rank4
0.2617923 0.2119375
exp(cbind(OR=coef(model), confint(model)))
Waiting for profiling to be done...
OR 2.5 % 97.5 %
(Intercept) 0.0185001 0.001889165 0.1665354
gre 1.0022670 1.000137602 1.0044457
gpa 2.2345448 1.173858216 4.3238349
rank2 0.5089310 0.272289674 0.9448343
rank3 0.2617923 0.131641717 0.5115181
rank4 0.2119375 0.090715546 0.4706961
关于r - 使用 or_glm() 函数调整优势比?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/72507134/