'huxreg - exponentiated coefficients and updated standard errors
I am running some CRR models from the package cmprsk. I am working towards outputting the results using huxreg. I have used tidy_args to get exponentiated coefficients, per this q&a, but it didn't have an answer on updating the standard errors along with the exp(coef)'s. SE's are really the value I want (because it matches the other tables I made using different regression analysis, and I want to carry that theme through the paper). Any advice on how I can do a workaround to get them?
library(cmprsk)
data(Melanoma, package = "MASS")
head(Melanoma)
covs1 <- model.matrix(~ Melanoma$sex)[, -1]
covs2 <- model.matrix(~ Melanoma$sex + Melanoma$age)[, -1]
covs3 <- model.matrix(~ Melanoma$sex*Melanoma$age)[, -1]
mel1 <- crr(ftime = Melanoma$time, fstatus = Melanoma$status, cov1 = covs1, cencode = 2)
mel2 <- crr(ftime = Melanoma$time, fstatus = Melanoma$status, cov1 = covs2, cencode = 2)
mel3 <- crr(ftime = Melanoma$time, fstatus = Melanoma$status, cov1 = covs3, cencode = 2)
summary(mel1)
summary(mel2)
summary(mel3)
huxreg(mel1, mel2, mel3, tidy_args = list(exponentiate = TRUE))
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|