shuffle_two_groups: Randomization for Two-Group Comparisons

In STATS250SBI/stats250sbi: Functions for Use in STATS 250 at the University of Michigan

Randomization for Two-Group Comparisons

Description

Shuffles data for use in two-group simulations.

Usage

shuffle_two_groups(d, groups)

Arguments

d	A data frame that contains the
groups	The name of the variable (in quotes!) that identifies which group each observation belongs to

Value

The original data frame with the group labels randomly shuffled among observations

Examples

# Make a data frame to shuffle
og_data <- data.frame(
  "group" = c(rep("Group A", 600), rep("Group B", 200)),
  "result" = c(rep("Failure", 402), rep("Success", 198),
               rep("Failure", 120), rep("Success", 80)),
  stringsAsFactors = TRUE)

# Tabulate successes & failures in each group in original data
table(og_data$result, og_data$group)

# Shuffle data with shuffle_two_groups
shuffle_data <- shuffle_two_groups(og_data, "group")

# Tabulate successes & failures in each group in shuffled data
table(shuffle_data$result, shuffle_data$group)

STATS250SBI/stats250sbi documentation built on March 18, 2022, 1:14 p.m.