In STATA with stmh I can get stratified rate ratios between two groups in a survival analysis as well as get a 95% confidence interval, chi-square, and p-value for that ratio. Is there anything similar in R?
So far I've gotten this far. Using the lung dataset from the survival package
library(tidyverse)
library(survival)
head(lung)
#> inst time status age sex ph.ecog ph.karno pat.karno meal.cal wt.loss
#> 1 3 306 2 74 1 1 90 100 1175 NA
#> 2 3 455 2 68 1 0 90 90 1225 15
#> 3 3 1010 1 56 1 0 90 90 NA 15
#> 4 5 210 2 57 1 1 90 60 1150 11
#> 5 1 883 2 60 1 0 100 90 NA 0
#> 6 12 1022 1 74 1 1 50 80 513 0
I've found survRate from biostat3 which can give stratified event rate information
library(biostat3)
survRate(Surv(time, status) ~ sex, data=lung)
#> sex tstop event rate lower upper
#> sex=1 1 39086 112 0.002865476 0.002359424 0.003447912
#> sex=2 2 30507 53 0.001737306 0.001301362 0.002272439
And can get the rate ratio by extracting the rate elements
#Get the rate for grade of 1
sex_1 <- survRate(Surv(time, status) ~ sex, data=lung) %>%
filter(sex == 1) %>%
purrr::pluck("rate")
#Get the rate for grade of 2
sex_2 <- survRate(Surv(time, status) ~ sex, data=lung) %>%
filter(sex == 2) %>%
purrr::pluck("rate")
#Get the ratio
sex_2 / sex_1
#> [1] 0.6062888
This is a good start, but in STATA with stmh I can also get a 95% confidence interval, chi-square, and p-value for that ratio. Is there anything similar in R?
