miss_analyze: Missing data dependencies

In Deleetdk/kirkegaard: kirkegaard

Missing data dependencies

Description

Calculates Cohen's d or equivalent for every variable pair. Larger values mean that cases with missing data in one variable differ from other cases in the other variable, thus that the data are not missing at random (MCAR).

Usage

miss_analyze(data, robust = F)

Arguments

data	(df/mat) Data.
robust	(lgl scalar) Whether to use robust measures (default false). If true, will use median/mad instead of mean/sd to calculate the standardized mean differences.

Details

This method was proposed by McKnight et al (2007) Missing Data: A Gentle Introduction.

Value

A data frame of size n x n where n is the number of variables in data. The rows are the gropuing variable (missing vs. not-missing) and the columns are the outcome variables.

Examples

miss_analyze(miss_add_random(iris))

Deleetdk/kirkegaard documentation built on April 27, 2024, 3:26 p.m.