report_cat_vars: Create a summary table for categorical variables and their...

In LukasWallrich/timesaveR: Functions to Accelerate (Academic) Data Analysis and Reporting

Create a summary table for categorical variables and their relationship with a continuous outcome variable

Description

This takes a set of categorical variables and a continuous dependent variable and produces a table that shows the distribution of data across the levels of the categorical variables, as well as the mean of the dependent variable for each level and the significance of pairwise comparisons between these means.

Usage

report_cat_vars(
  data,
  dv,
  ...,
  var_names = NULL,
  level_names = NULL,
  p_adjust = p.adjust.methods,
  alpha_level = 0.05,
  filename = NULL,
  notes = list(),
  dv_name = NULL,
  bold_vars = TRUE,
  apa_style = TRUE,
  css_tags = list(),
  na.rm = TRUE,
  exclude_na = FALSE
)

Arguments

data	Dataframe containing the variables specified
dv	The continuous dependent variable to be presented alongside the levels of categorical variables. Set to NULL to just show the distribution of the categorical variables.
...	Categorical variables to be included
var_names	Tibble of old and new variable names, if variables are to be renamed for display. See get_rename_tribbles() for required format
level_names	Tibble of old and new level names, if levels are to be renamed for display. See get_rename_tribbles() for required format
p_adjust	One of p_adjust.methods, defaults to Holm
alpha_level	The level of significance for the pairwise comparisons (after p.adjust). Defaults to .05
filename	If provided, the table will be saved as an HTML file with this name.
notes	List of notes to append to bottom of table.
dv_name	Optional. A different name to use for the dependent variable in the automatic table footnote explaining the M(SD) column. Defaults to dv.
bold_vars	Should rows with variable names be bold. Defaults to TRUE
apa_style	Logical, should APA-style formatting be applied
css_tags	List of css tags to be added, each named with the class that the tag should be added to.
na.rm	Should missing values be dropped in the dv when summary statistics are calculated?
exclude_na	Should cases that are NA on a categorical variable be dropped from that section?

Value

A list including a tibble of descriptive statistics (descr), the gt-table (tab) and the HTML code (html_code) with css_tags added

Examples

report_cat_vars(iris, Sepal.Length, Species)

# You can rename variables and levels reasonably easily
# Use get_rename_tribbles() to get the basis of these tibbles

var_renames <- tibble::tribble(
 ~old,     ~new,     
 "gndr",   "Gender",  
 "cntry",  "Country"
 )

level_renames <- tibble::tribble(
 ~var,     ~level_old, ~level_new, 
 "gndr",   "1",        "male",       
 "gndr",   "2",        "female",       
 "cntry",  "DE",       "Germany",      
 "cntry",  "FR",       "France",      
 "cntry",  "GB",       "UK"
 )
 
report_cat_vars(ess_health, health, gndr, cntry, var_names = var_renames, 
             level_names = level_renames)

LukasWallrich/timesaveR documentation built on Nov. 29, 2024, 4:47 a.m.