In andr3wli/powerPsych: Effect Size and Power Toolbox for Psychologists

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

library(powerPsych)

Examples

An effect size is a standardized way to report the strength of an apparent relationship. If you are comparing two populations/group, you can use this function to compute the effect size of the difference between the two means. Typically, Cohen's d is categorized as follows:

| cohen's d | Interpretation | |-----------|-----------------| | 0.2 | A small effect | | 0.5 | A medium effect | | 0.8+ | A large effect |

cohens_d consumes the mean and standard deviation of the two samples to generate a statistic and interpretation. If the standard deviation is the same, type sd = same and only enter the one standard deviation. Entering two standard deviations will result in the function ignoring the second input. At this point, the function will use the pooled standard deviation. Here is an example for sd = same:

# same sd
cohens_d(0, 1, 0.54, sd = "same")

#when you input 2 standard deviations
cohens_d(0, 1, 0.54, 0.6, sd = "same")

When the standard deviation are different, enter two inputs and type sd = diff. If the user enters only input, there is an expected error message that prompts the user to add the second input. Here are some examples:

# different sd
cohens_d(0, 1, 0.54, 0.6, sd = "diff")

# expected error when only sd is entered and if user indicated "diff"
# cohens_d(0, 1, 0.54, sd = "diff")
# If the standard deviation of the groups are different, you must enter a value for sd.two