center {mlmhelpr}

Automatically grand-mean or group-mean center a fitted object

Description

This function refits a model using grand-mean centering, group-mean centering (if a grouping variable is specified), or centering at a user-specified value

Usage

center(
  x,
  grand_variables = NULL,
  group = NULL,
  group_variables = NULL,
  value = NULL,
  value_variables = NULL
)

Arguments

x

A model produced using the lme4::lmer() function. This is an object of class merMod and subclass lmerMod.

grand_variables

one or more variables to center at the grand-mean

group

Grouping variable. If a grouping variable is specified, group-mean centering (also known as centering within cluster) based on that variable will be performed.

group_variables

Variables to be group-mean centered.

value

Center at a specific value rather than the grand mean

value_variables

Variables to be centered at user-specified value rather than the grand mean

Value

A newly fitted model with centered variables

Examples

fit <- lme4::lmer(mathach ~ 1 + ses + catholic + (1|id),
data=hsb, REML=TRUE)

# Centering a single variable around the grand mean
fit_gmc <- center(fit, grand_variables="ses")

# Centering multiple variables around the grand mean
fit_gmc <- center(fit, grand_variables=c("ses", "catholic"))

# Centering variables around the group means
fit_cwg <- center(fit, group="id", group_variables="ses")

# Centering variables using different strategies
fit_mixed <- center(fit, group = "id", group_variables = "ses", grand_variables = "catholic")