sumvar (version 0.1)

dist_sum: Explore a continuous variable.

Description

Summarises the median, interquartile range, mean, standard deviation, confidence intervals of the mean and produces a density plot, stratified by a second grouping variable.

Provides frequentist hypothesis tests for comparison between groups: T test and Wilcoxon rank sum for 2 groups, Anova and Kruskall wallis test for 3 or more groups.

The function accepts an input from a dplyr pipe "%>%" and outputs the results as a tibble.

Usage

dist_sum(data, var, by = NULL)

Value

A tibble with a summary of the variable frequency (n), number of missing observations (n_miss), median, interquartile range, mean, SD, 95% confidence intervals of the mean (using the Z distribution), and density plots.

Shows the T test (p_ttest) and Wilcoxon rank sum (p_wilcox) hypothesis tests when there are two groups And an Anova test (p_anova) and Kruskal-Wallis test (p_kruskal) when there are three or more groups.

Arguments

data

The data frame or tibble

var

The variable you would like to summarise

by

The grouping variable

Examples

example_data <- dplyr::tibble(id = 1:100, age = rnorm(100, mean = 30, sd = 10),
                              group = sample(c("a", "b", "c", "d"),
                              size = 100, replace = TRUE))
dist_sum(example_data, age, group)
example_data <- dplyr::tibble(id = 1:100, age = rnorm(100, mean = 30, sd = 10),
                             sex = sample(c("male", "female"),
                             size = 100, replace = TRUE))
dist_sum(example_data, age, sex)
summary <- dist_sum(example_data, age, sex) # Save summary statistics as a tibble.