Skip to contents

Pool contrasts and comparisons from test_predictions()

Source: R/pool_comparisons.R
pool_comparisons.Rd

This function "pools" (i.e. combines) multiple ggcomparisons objects, returned by test_predictions(), in a similar fashion as mice::pool().

Usage

pool_comparisons(x, ...)

Arguments

x

A list of ggcomparisons objects, as returned by test_predictions().

...

Currently not used.

Value

A data frame with pooled comparisons or contrasts of predictions.

Details

Averaging of parameters follows Rubin's rules (Rubin, 1987, p. 76).

References

Rubin, D.B. (1987). Multiple Imputation for Nonresponse in Surveys. New York: John Wiley and Sons.

Examples

data("nhanes2", package = "mice")
imp <- mice::mice(nhanes2, printFlag = FALSE)
comparisons <- lapply(1:5, function(i) {
  m <- lm(bmi ~ age + hyp + chl, data = mice::complete(imp, action = i))
  test_predictions(m, "age")
})
pool_comparisons(comparisons)
#> Model-based Contrasts Analysis
#> 
#> Level1 | Level2 | Difference |          95% CI | t(20) |      p
#> ---------------------------------------------------------------
#> 40-59  | 20-39  |      -5.84 | [-10.22, -1.47] | -4.07 | < .001
#> 60-99  | 20-39  |      -7.22 | [-12.34, -2.09] | -4.27 | < .001
#> 60-99  | 40-59  |      -1.37 | [ -5.53,  2.79] | -0.85 |  0.404
#> 
#> Variable predicted: bmi
#> Predictors contrasted: age
#> Predictors averaged: hyp, chl (2e+02)
#>