readLisrel: Read LISREL matrices into R
In lisrelToR: Import Output from LISREL into R

View source: R/readLisrel.R

readLisrel

R Documentation

Read LISREL matrices into R

Description

This function scans LISREL (Joreskog & Sorbom, 1996) output for model matrices and fit indices.

Usage

readLisrel(x)

Arguments

`x`	String indicating the location of a LISREL output file.

Details

LisrelToR uses the following names for the model matrices:

LY: Lambda-Y matrix.
PS: Psi matrix.
BE: Beta matrix.
TE: Theta-Epsilon matrix.
TY: Tau-Y matrix.
AL: Alpha matrix.
LX: Lambda-X matrix.
PH: Phi matrix.
GA: Gamma matrix.
TD: Theta-Delta matrix.
TX: Tau-X matrix.
KA: Kappa
ObsCovs: The observed covariance matrix, or a list of such matrices for each group.
ImpCovs: The implied covariance matrix, or a list of such matrices for each group.

Furthermore, lisrelToR uses the following names for matrix types:

est: Parameter estimates
se: Standard errors
t: t-values
parSpec: Parameter numbers

Value

A list of class "lisrel" contaning:

`fitIndices`	Fit indices, currently not supported.
`matrices`	A list contaning the model matrices. For each group this list conains a list with for each matrix (using LISREL style naming, see details) a list contaning elements `est` for parameter estimates, `se` for standard errors, `t` for t-values and `parSpec` for parameter numbers. Use `lisrelMatrix` to extract the matrices.
`variables`	Currently not used.
`Covariances`	A list with elements `implied` and `observed` containing the implied and observed covariance matrices.

Author(s)

Sacha Epskamp <mail@sachaepskamp.com>

References

Joreskog, K. G., & Sorbom, D. (1996). LISREL 8 user's reference guide. Scientific Software.

Examples

## Measurment invariance example:
modFile <- system.file("extdata", "mi1.OUT", package = "lisrelToR")
Lis <- readLisrel(modFile)

# Extract Lambda-Y for group 2:
lisrelMatrix(Lis,"LY", group = 2)

# Structure of object:
str(Lis)

# Print full LISREL output to console:
print(Lis)

lisrelToR documentation built on June 22, 2024, 11:40 a.m.