Error: attempt to apply non-function in tbl_uvregression from gtsummary

Question

when I attempt to use tbl_uvregression from the gtsummary package I keep getting an error message about attempting to apply a non-function.

Here is an example:

library(gtsummary)
library(tidyverse)
packageVersion("gtsummary")
# package 1.7.0

data("mtcars")

cars <- mtcars %>% 
    dplyr::select(mpg, disp, cyl, hp) %>% 
tbl_uvregression(
    method = "lm",
    y = hp,
    exponentiate = TRUE,
)

# Performing individual univariate linear regression works just fine
lm(hp ~ mpg, data = cars)
lm(hp ~ disp, data = cars)
lm(hp ~ cyl, data = cars)

I get the following error message: There was an error constructing model "lm"(formula = hp ~ mpg, data = .) See error below. Error in mutate(): ℹ In argument: model = map(...). Caused by error in value[[3L]](): ! Error in eval(.): attempt to apply non-function Run rlang::last_error() to see where the error occurred.

Can someone tell me what I am doing wrong?

PS: I really enjoy using gtsummary, many thanks for creating this excellent package!

Answer 1

I made two small changes.

1. Unquoted method = lm.
2. Change exponentiate = FALSE because TRUE is not valid for lm() models.

library(gtsummary)
packageVersion("gtsummary")
#> [1] '1.7.0'

mtcars %>% 
  select(mpg, disp, cyl, hp) %>% 
  tbl_uvregression(
    method = lm,
    y = hp,
    exponentiate = FALSE, # TRUE is not valid for lm() models
  ) %>%
  as_kable() # convert to kable to display on stackoverflow

Characteristic	N	Beta	95% CI	p-value
mpg	32	-8.8	-12, -6.2	<0.001
disp	32	0.44	0.31, 0.56	<0.001
cyl	32	32	24, 40	<0.001

^{Created on 2023-02-26 with reprex v2.0.2}