subsem: User-level function with user-defined interestingness measure

In langenberg/subgroupsem: Subgroup Discovery in Structural Equation Models

User-level function with user-defined interestingness measure

Description

todo

Usage

subsem(
  model,
  data,
  qf = NULL,
  predictors = NULL,
  group = NULL,
  subsem_options = list(),
  lavaan_options = list()
)

Arguments

model	a lavaan model syntax (a character vector)
data	a data frame
qf	a lavaan syntax-based computation of the interestingness measure, where the interestingness measure has to be named *subsem_qf*. Can also be included directly in the model syntax (then, here NULL, as is default)
predictors	a character vector of variable names, which are used as covariates/predictors in the subgroup discovery (variables in data)
group	An additional group variable for subgroup discovery in multigroup models.
subsem_options	A list of additional options passed to the subgroupsem main function
lavaan_options	A list of additional options passed to the lavaan main function

Value

List containing the time consumed and the groups.

Examples

# Define lavaan model
model <- "
eta1 =~ NA*x1 + c(la21,la22)*x2 + x3
eta2 =~ NA*x4 + c(la51,la52)*x5 + x6
eta3 =~ NA*x7 + c(la81,la82)*x8 + x9

eta1 ~~ 1*eta1
eta2 ~~ 1*eta2
eta3 ~~ 1*eta3

eta1 + eta2 + eta3 ~ 0*1

subsem_qf := abs(la21 - la22)
"

# Pass model, data and names of predictors to function
m1 <- subsem(
  model = model,
  data = lavaan::HolzingerSwineford1939,
  qf = NULL,
  predictors = c("sex", "school", "grade")
)
summary(m1)

langenberg/subgroupsem documentation built on Nov. 22, 2023, 2:37 a.m.