过时的数据掩码太迟解决

大家好，我有一个关于非标准评估的问题。我拟合了几个具有不同结果变量的模型，并像这样计算边际效应。

library(palmerpenguins)
library(marginaleffects)
library(sandwich)
library(tidyr)
library(dplyr)


long_pengs = penguins |>
  pivot_longer(cols = c(body_mass_g, flipper_length_mm),
               names_to = 'outcome',
              values_to = 'vals') |>
  drop_na(sex) |>
  summarise(mods = list(lm(vals ~ sex * bill_length_mm, data = pick(everything()))), .by = outcome)


comps = long_pengs |>
  rowwise(outcome) |>
  reframe(avg_comparisons(mods,
                          variables = 'sex',
                          subset(sex == 'female')))

但是，当我尝试对标准错误进行聚类引导时，我遇到了这些错误消息，我想知道如何解决这个问题。我并不坚持使用非标准评估来做到这一点。

# works 
long_pengs |> 
  rowwise(outcome) |>
  reframe(avg_comparisons(mods,
    variables = 'sex',
    subset(sex == 'female')) |>
      inferences(method = 'rsample')) 

long_pengs |>
rowwise(outcome) |>
reframe(avg_comparisons(mods,
                        variables = 'sex',
                        subset(sex == 'female'),
                        vcov = vcovBS(mods, cluster = ~species)))
#> Error in `reframe()`:
#> ℹ In argument: `avg_comparisons(...)`.
#> ℹ In row 1.
#> Caused by error:
#> ! Obsolete data mask.
#> ✖ Too late to resolve `species` after the end of `dplyr::summarise()`.
#> ℹ Did you save an object that uses `species` lazily in a column in the
#>   `dplyr::summarise()` expression ?

long_pengs |> 
  rowwise(outcome) |>
  reframe(avg_comparisons(mods,
    variables = 'sex',
    subset(sex == 'female')) |>
      inferences(method = 'rsample', strata = species))
#> Error in `reframe()`:
#> ℹ In argument: `inferences(...)`.
#> ℹ In row 1.
#> Caused by error:
#> ! object 'species' not found

期望的输出看起来是这样的

## desired output 

m1 = lm(body_mass_g ~ sex * bill_length_mm, data = penguins)

c1 = avg_comparisons(m1, variables = 'sex',
                     subset(sex == 'female'),
                    vcov = vcovBS(m1, cluster = ~species))

m2 = lm(flipper_length_mm ~ sex * bill_length_mm, data = penguins)

c2 = avg_comparisons(m2, variables = 'sex',
                     subset(sex == 'female'),
                     vcov = vcovBS(m2, cluster = ~species))

rbind(c1, c2)
#> 
#>  Estimate Std. Error     z Pr(>|z|)   S   2.5 % 97.5 %
#>   420.487     293.10 1.435    0.151 2.7 -153.97  994.9
#>     0.392       5.16 0.076    0.939 0.1   -9.73   10.5
#> 
#> Term: sex
#> Type:  response 
#> Comparison: mean(male) - mean(female)
#> Columns: term, contrast, estimate, std.error, statistic, p.value, s.value, conf.low, conf.high, predicted_lo, predicted_hi, predicted

^{创建于 2024-11-13，使用reprex v2.1.1}