symSEM (version 0.4)

JacobianRAM: Compute a Jacobian Matrix of the Implied Covariance/Correlation Matrix based on a RAM model.

Description

It computes a symbolic Jacobian matrix of the model-implied covariance (or correlation) matrix in SEM using the RAM specification.

Usage

JacobianRAM(RAM, vars, corr = FALSE)

Value

A Jacobian matrix.

Arguments

RAM

A RAM object including a list of matrices of the model returned from lavaan2RAM

vars

A vector of characters of the random variables. If the random variables are not listed in `vars`, they are treated as constants. If `vars` is missing, all names in `RAM` are treated as random variables.

corr

Whether the model implied matrix is covariance (default) or correlation structure.

Author

Mike W.-L. Cheung <[e-mail]>

Examples

if (FALSE) {

#### A mediation model
model1 <- "y ~ c*x + b*m
           m ~ a*x
           ## Means
           y ~ b0*1
           m ~ m0*1
           x ~ x0*1"

RAM1 <- metaSEM::lavaan2RAM(model1)

## Model-implied covariance matrix and mean structure
JacobianRAM(RAM1, corr=FALSE)

## Model-implied correlation matrix
JacobianRAM(RAM1, corr=TRUE)

#### A CFA model
model2 <- "f =~ x1 + x2 + x3 + x4#'
           ## Mean
           f ~ fmean*1"

RAM2 <- metaSEM::lavaan2RAM(model2)

## Model-implied covariance matrix
JacobianRAM(RAM2, corr=FALSE)

## Model-implied correlation matrix
JacobianRAM(RAM2, corr=TRUE)
}