umxLISREL: Make a LISREL model analogous to umxRAM

In umx: Structural Equation Modeling and Twin Modeling in R

Make a LISREL model analogous to umxRAM

Description

umxLISREL is a wrapper for OpenMx::mxModel() with type="LISREL". It automatically partitions manifest and latent variables into endogenous and exogenous sets, inserts data, handles raw/covariance types, adds means if raw data are used, handles ordinal variables, runs the model, and displays summaries.

Usage

umxLISREL(
  model = NA,
  ...,
  data = NULL,
  manifestVars = NULL,
  latentVars = NULL,
  name = NA,
  group = NULL,
  group.equal = NULL,
  suffix = "",
  comparison = TRUE,
  type = c("Auto", "FIML", "cov", "cor", "WLS", "DWLS", "ULS"),
  weight = NULL,
  allContinuousMethod = c("cumulants", "marginals"),
  autoRun = getOption("umx_auto_run"),
  tryHard = c("no", "yes", "ordinal", "search"),
  std = FALSE,
  refModels = NULL,
  remove_unused_manifests = TRUE,
  independent = NA,
  setValues = TRUE,
  optimizer = NULL,
  verbose = FALSE,
  std.lv = FALSE,
  printTab = FALSE
)

Arguments

model	NA, a name string, or an existing LISREL OpenMx::mxModel() to update.
...	Path statements (mxPath or umxPath), matrices, etc., to add to the model.
data	Data frame, matrix, or mxData to use.
manifestVars	Optional list of endogenous/exogenous manifest variables, or character vector of manifest variables to partition.
latentVars	Optional list of endogenous/exogenous latent variables, or character vector of latent variables to partition.
name	Optional name for the model (defaults to the model's current name or 'm1').
group	Column name in data to partition data for multi-group models.
group.equal	Not implemented.
suffix	Suffix to append to parameter labels.
comparison	Compare the model to saturated models in summary (Default = TRUE).
type	Data type: "Auto" (guesses), "FIML", "cov", "cor", "WLS", "DWLS", "ULS".
weight	Weight column name.
allContinuousMethod	Method for continuous variables when WLS is used.
autoRun	Run the model (default = TRUE).
tryHard	How to run the model: "no", "yes", "ordinal", "search".
std	Standardize output (Default = FALSE).
refModels	Reference models for summary comparison.
remove_unused_manifests	Remove manifests not used in paths (Default = TRUE).
independent	Whether the model is independent (Default = NA).
setValues	Automatically set starting values (Default = TRUE).
optimizer	Set the optimizer to use.
verbose	Print diagnostic info.
std.lv	Standardize latent variables (Default = FALSE).
printTab	Print parameter table.

Value

A LISREL OpenMx::mxModel()

References

https://github.com/tbates/umx, https://tbates.github.io

See Also

umxRAM(), plot.MxLISRELModel(), xmu_standardize_LISREL()

Other Core Model Building Functions: umx, umxMatrix(), umxModify(), umxPath(), umxRAM(), umxRAM_DE(), umxSuperModel()

Examples

## Not run: 
library(umx)
data(demoOneFactor)
manifests = names(demoOneFactor)

# 1. LISREL model with covariance data
m1 = umxLISREL("one_factor_cov", data = demoOneFactor, type = "cov",
	umxPath("G", to = manifests),
	umxPath(var = manifests),
	umxPath(var = "G", fixedAt = 1)
)

# 2. LISREL model with raw data (means are automatically added)
m2 = umxLISREL("one_factor_raw", data = demoOneFactor,
               umxPath("G", to = manifests),
               umxPath(var = manifests),
               umxPath(var = "G", fixedAt = 1))

# 3. Forced exogenous manifests using manifestVars list override
m3 = umxLISREL("forced_exogenous", data = demoOneFactor,
               manifestVars = list(endogenous = c("x4", "x5"), exogenous = c("x1", "x2")),
               latentVars = list(endogenous = "G", exogenous = "xi"),
               umxPath("xi", to = c("x1", "x2")),
               umxPath("G", to = c("x4", "x5")),
               umxPath("xi", to = "G"),
               umxPath(var = c("x1", "x2", "x4", "x5")),
               umxPath(var = "xi", fixedAt = 1),
               umxPath(var = "G"),
               umxPath(means = c("x1", "x2", "x4", "x5")))

## End(Not run)

umx documentation built on Oct. 11, 2026, 5:07 p.m.