parameters (version 0.10.1)

model_parameters.mira: Parameters from multiply imputed repeated analyses

Description

Format models of class mira, obtained from mice::width.mids().

Usage

# S3 method for mira
model_parameters(
  model,
  ci = 0.95,
  exponentiate = FALSE,
  p_adjust = NULL,
  verbose = TRUE,
  ...
)

Arguments

model

An object of class mira.

ci

Confidence Interval (CI) level. Default to 0.95 (95%).

exponentiate

Logical, indicating whether or not to exponentiate the the coefficients (and related confidence intervals). This is typical for, say, logistic regressions, or more generally speaking: for models with log or logit link. Note: standard errors are also transformed (by multiplying the standard errors with the exponentiated coefficients), to mimic behaviour of other software packages, such as Stata.

p_adjust

Character vector, if not NULL, indicates the method to adjust p-values. See p.adjust for details.

verbose

Toggle warnings and messages.

...

Arguments passed to or from other methods.

Details

model_parameters() for objects of class mira works similar to summary(mice::pool()), i.e. it generates the pooled summary of multiple imputed repeated regression analyses.

Examples

# NOT RUN {
library(parameters)
if (require("mice")) {
  data(nhanes2)
  imp <- mice(nhanes2)
  fit <- with(data = imp, exp = lm(bmi ~ age + hyp + chl))
  model_parameters(fit)
}
# }
# NOT RUN {
# model_parameters() also works for models that have no "tidy"-method in mice
if (require("mice") && require("gee")) {
  data(warpbreaks)
  set.seed(1234)
  warpbreaks$tension[sample(1:nrow(warpbreaks), size = 10)] <- NA
  imp <- mice(warpbreaks)
  fit <- with(data = imp, expr = gee(breaks ~ tension, id = wool))

  # does not work:
  # summary(pool(fit))

  model_parameters(fit)
}
# }
# NOT RUN {


# and it works with pooled results
if (require("mice")) {
  data("nhanes2")
  imp <- mice(nhanes2)
  fit <- with(data = imp, exp = lm(bmi ~ age + hyp + chl))
  pooled <- pool(fit)

  model_parameters(pooled)
}
# }