[Maturing] Collection of tidiers that can be passed to tbl_regression() and tbl_uvregression() to obtain modified results. See examples below.

tidy_standardize(
  x,
  exponentiate = FALSE,
  conf.level = 0.95,
  conf.int = TRUE,
  ...,
  quiet = FALSE
)

tidy_bootstrap(
  x,
  exponentiate = FALSE,
  conf.level = 0.95,
  conf.int = TRUE,
  ...,
  quiet = FALSE
)

tidy_robust(
  x,
  exponentiate = FALSE,
  conf.level = 0.95,
  conf.int = TRUE,
  vcov_estimation = NULL,
  vcov_type = NULL,
  vcov_args = NULL,
  ...,
  quiet = FALSE
)

pool_and_tidy_mice(x, pool.args = NULL, ..., quiet = FALSE)

tidy_gam(x, conf.int = FALSE, exponentiate = FALSE, conf.level = 0.95, ...)

Arguments

x

a regression model object

exponentiate

Logical indicating whether or not to exponentiate the the coefficient estimates. This is typical for logistic and multinomial regressions, but a bad idea if there is no log or logit link. Defaults to FALSE.

conf.level

The confidence level to use for the confidence interval if conf.int = TRUE. Must be strictly greater than 0 and less than 1. Defaults to 0.95, which corresponds to a 95 percent confidence interval.

conf.int

Logical indicating whether or not to include a confidence interval in the tidied output. Defaults to FALSE.

...

arguments passed to method;

  • pool_and_tidy_mice(): mice::tidy(x, ...)

  • tidy_standardize(): effectsize::standardize_parameters(x, ...)

  • tidy_bootstrap(): parameters::bootstrap_parameters(x, ...)

  • tidy_robust(): parameters::model_parameters(x, ...)

quiet

Logical indicating whether to print messages in console. Default is FALSE

vcov_estimation, vcov_type, vcov_args

arguments passed to parameters::model_parameters()

pool.args

named list of arguments passed to mice::pool() in pool_and_tidy_mice(). Default is NULL

Details

  • tidy_standardize() tidier to report standardized coefficients. The effectsize package includes a wonderful function to estimate standardized coefficients. The tidier uses the output from effectsize::standardize_parameters(), and merely takes the result and puts it in broom::tidy() format.

  • tidy_bootstrap() tidier to report bootstrapped coefficients. The parameters package includes a wonderful function to estimate bootstrapped coefficients. The tidier uses the output from parameters::bootstrap_parameters(test = "p"), and merely takes the result and puts it in broom::tidy() format.

  • tidy_robust() tidier to report robust standard errors, confidence intervals, and p-values. The parameters package includes a wonderful function to calculate robust standard errors, confidence intervals, and p-values The tidier uses the output from parameters::model_parameters(), and merely takes the result and puts it in broom::tidy() format. To use this function with tbl_regression(), pass a function with the arguments for tidy_robust() populated. This is easily done using purrr::partial() e.g. tbl_regression(tidy_fun = partial(tidy_robust, vcov_estimation = "CL"))

  • pool_and_tidy_mice() tidier to report models resulting from multiply imputed data using the mice package. Pass the mice model object before the model results have been pooled. See example.

Ensure your model type is compatible with the methods/functions used to estimate the model parameters before attempting to use the tidier with tbl_regression()

Example Output

Example 1

Example 2

Example 3

Examples

# \donttest{
# Example 1 ----------------------------------
mod <- lm(age ~ marker + grade, trial)

tbl_stnd <- tbl_regression(mod, tidy_fun = tidy_standardize)
#> tidy_standardize(): Estimating standardized coefs with
#> `effectsize::standardize_parameters(model = x, ci = 0.95)`
tbl <- tbl_regression(mod)

tidy_standardize_ex1 <-
  tbl_merge(
    list(tbl_stnd, tbl),
    tab_spanner = c("**Standardized Model**", "**Original Model**")
  )

# Example 2 ----------------------------------
# use "posthoc" method for coef calculation
tidy_standardize_ex2 <-
  tbl_regression(mod, tidy_fun = purrr::partial(tidy_standardize, method = "posthoc"))
#> tidy_standardize(): Estimating standardized coefs with
#> `effectsize::standardize_parameters(model = x, ci = 0.95, method = "posthoc")`

# Example 3 ----------------------------------
# Multiple Imputation using the mice package
set.seed(1123)
pool_and_tidy_mice_ex3 <-
  suppressWarnings(mice::mice(trial, m = 2)) %>%
  with(lm(age ~ marker + grade)) %>%
  tbl_regression()
#> 
#>  iter imp variable
#>   1   1  age  marker  response
#>   1   2  age  marker  response
#>   2   1  age  marker  response
#>   2   2  age  marker  response
#>   3   1  age  marker  response
#>   3   2  age  marker  response
#>   4   1  age  marker  response
#>   4   2  age  marker  response
#>   5   1  age  marker  response
#>   5   2  age  marker  response
#> pool_and_tidy_mice(): Tidying mice model with
#> `mice::pool(x) %>% mice::tidy(exponentiate = FALSE, conf.int = TRUE, conf.level = 0.95)`
# }