Bug Report: warning with tbl_regression for glm with subset

[richardjtelford]

I am using tbl_regression() to report the result of a glm. The glm uses the subset argument to remove some unneeded data.

tbl_regression() is giving a warning. The results appear to be correct.

With an lm model, no warning is given.

set.seed(23)
df <- data.frame(
  resp = rnorm(n = 60),
  pred = rep(c("A", "B"), 30), 
  n = 1:60
)

mod1 <- glm(resp ~ pred, data = df[1:50, ]) # without subset argument
mod2 <- glm(resp ~ pred, data = df, subset = n <= 50) # with subset

# models should be the same
identical(coef(mod1), coef(mod2))
#> [1] TRUE


gtsummary::tbl_regression(mod1)

Characteristic	Beta	95% CI1	p-value
pred
A	—	—
B	0.03	-0.46, 0.52	>0.9
1 CI = Confidence Interval

gtsummary::tbl_regression(mod2)
#> Warning in tcm * w: longer object length is not a multiple of shorter object
#> length

Characteristic	Beta	95% CI1	p-value
pred
A	—	—
B	0.03	-0.46, 0.52	>0.9
1 CI = Confidence Interval

^{Created on 2024-12-23 with reprex v2.1.1}

[ddsjoberg]

Thanks for the post @richardjtelford !

This warning arises from the broom.helpers::tidy_plus_plus(). Do you mind posting the issue there, please? https://github.com/larmarange/broom.helpers

glm(mpg ~ gear, data = mtcars, subset = mpg < 30) |> 
  broom.helpers::tidy_plus_plus()
#> Warning in tcm * w: longer object length is not a multiple of shorter object
#> length
#> # A tibble: 1 × 17
#>   term  variable var_label var_class var_type   var_nlevels contrasts
#>   <chr> <chr>    <chr>     <chr>     <chr>            <int> <chr>    
#> 1 gear  gear     gear      numeric   continuous          NA <NA>     
#> # ℹ 10 more variables: contrasts_type <chr>, reference_row <lgl>, label <chr>,
#> #   n_obs <dbl>, estimate <dbl>, std.error <dbl>, statistic <dbl>,
#> #   p.value <dbl>, conf.low <dbl>, conf.high <dbl>

^{Created on 2024-12-23 with reprex v2.1.1}

[ddsjoberg]

Thanks @richardjtelford !