model.lavaan: Build the data generation template and analysis template from the lavaan result

Description

Creates a data generation and analysis template (lavaan parameter table) for simulations with the lavaan-class result. Model misspecification may be added into the template by a vector, a matrix, or a list of vectors or matrices (for multiple groups).

Usage

model.lavaan(object, std = FALSE, LY = NULL, PS = NULL, RPS = NULL, 
	TE = NULL, RTE = NULL, BE = NULL, VTE = NULL, VY = NULL, VPS = NULL, 
	VE=NULL, TY = NULL, AL = NULL, MY = NULL, ME = NULL, KA = NULL, 
	GA = NULL)

Value

SimSem object that contains the data generation template (@dgen) and analysis template (@pt).

Arguments

object: A lavaan-class object to be used to build the data generation and analysis template.
std: If TRUE, use the resulting standardized parameters for data generation. If FALSE, use the unstandardized parameters for data generation.
LY: Model misspecification in factor loading matrix from endogenous factors to Y indicators (need to be a matrix or a list of matrices).
PS: Model misspecification in residual covariance matrix among endogenous factors (need to be a symmetric matrix or a list of symmetric matrices).
RPS: Model misspecification in residual correlation matrix among endogenous factors (need to be a symmetric matrix or a list of symmetric matrices).
TE: Model misspecification in measurement error covariance matrix among Y indicators (need to be a symmetric matrix or a list of symmetric matrices).
RTE: Model misspecification in measurement error correlation matrix among Y indicators (need to be a symmetric matrix or a list of symmetric matrices).
BE: Model misspecification in regression coefficient matrix among endogenous factors (need to be a symmetric matrix or a list of symmetric matrices).
VTE: Model misspecification in measurement error variance of indicators (need to be a vector or a list of vectors).
VY: Model misspecification in total variance of indicators (need to be a vector or a list of vectors). NOTE: Either measurement error variance or indicator variance is specified. Both cannot be simultaneously specified.
VPS: Model misspecification in residual variance of factors (need to be a vector or a list of vectors).
VE: Model misspecification in total variance of of factors (need to be a vector or a list of vectors). NOTE: Either residual variance of factors or total variance of factors is specified. Both cannot be simulatneously specified.
TY: Model misspecification in measurement intercepts of Y indicators. (need to be a vector or a list of vectors).
AL: Model misspecification in endogenous factor intercept (need to be a vector or a list of vectors).
MY: Model misspecification in overall Y indicator means. (need to be a vector or a list of vectors). NOTE: Either measurement intercept of indicator mean can be specified. Both cannot be specified simultaneously.
ME: Model misspecification in total mean of endogenous factors (need to be a vector or a list of vectors). NOTE: Either endogenous factor intercept or total mean of endogenous factor is specified. Both cannot be simultaneously specified.
KA: Model misspecification in regression coefficient matrix from covariates to indicators (need to be a matrix or a list of matrices). KA is applicable when exogenous covariates are specified only.
GA: Model misspecification in regression coefficient matrix from covariates to factors (need to be a matrix or a list of matrices). KA is applicable when exogenous covariates are specified only.

Author

Sunthud Pornprasertmanit (psunthud@gmail.com)

Examples

Run this code

library(lavaan)
HS.model <- ' visual  =~ x1 + x2 + x3
             textual =~ x4 + x5 + x6
             speed   =~ x7 + x8 + x9 '

fit <- cfa(HS.model, data=HolzingerSwineford1939)

# Create data generation and data analysis model from lavaan
# Data generation is based on standardized parameters
datamodel1 <- model.lavaan(fit, std=TRUE)

# Data generation is based on unstandardized parameters
datamodel2 <- model.lavaan(fit, std=FALSE)

# Data generation model with misspecification on cross-loadings
crossload <- matrix("runif(1, -0.1, 0.1)", 9, 3)
crossload[1:3, 1] <- 0
crossload[4:6, 2] <- 0
crossload[7:9, 3] <- 0
datamodel3 <- model.lavaan(fit, std=TRUE, LY=crossload)