Getting confint to work with the rms lrm object

glm, r

Solution

Try this:

> summary(fit)[ , c("Lower 0.95", "Upper 0.95")]
               Lower 0.95   Upper 0.95
gear        -6.148918e+01 9.756505e+01
 Odds Ratio  1.975094e-27 2.354854e+42
mpg         -1.063706e+00 6.028564e+00
 Odds Ratio  3.451743e-01 4.151185e+02

(These results suggest complete separation or some other modeling pathology.)

Problem

I can't get the logistic regression from the rms package to work with confint(), here's an example: ``` library(rms) data(mtcars) dd <- datadist(mtcars) options(datadist = "dd") fit <- lrm(am ~ gear + mpg, data=mtcars) confint(fit) ``` This gives the error: Error: $ operator is invalid for atomic vectors And the traceback() gives: ``` 4: profile.glm(object, which = parm, alpha = (1 - level)/4, trace = trace) 3: profile(object, which = parm, alpha = (1 - level)/4, trace = trace) 2: confint.glm(fit) 1: confint(fit) ``` I guess the confint isn't implemented for the lrm() model. My question Is there a convenient alternative to way? Is there some other alternative created for the rms package?

Original source