LISREL - Support

SSI, Inc. offers a technical support service via e-mail. This service is only available to registered end users of the SSI software products. Click here to view SSI’s policy and procedures for obtaining technical support.

This service applies to problems in using the software and does not include statistical consultation. If you need help with modeling concepts and interpretation, please consult our short list of relevant text books or post a question to Semnet: A structural equation modeling discussion network.

If you require statistical consultation service, VPG Health would be pleased to be of assistance. Contact the VPG Health at sales@vpghealth.com for more information.

Please note that the program may not be able to read special characters such as ė, ö, ý, ş, etc. not used in English. Users should take care to avoid the use of these in either path or file names when using LISREL.

Documentation

• Graphical User Interface

• Quickstart Guide

• SIMPLIS Syntax Guide

• PRELIS Syntax Guide

• LISREL Syntax Guide

• Multilevel Modeling Guide

• Multilevel Generalized Linear Modeling Guide

• Analysis of Non-Normal Complex Survey Data Guide

• SIMPLIS, LISREL and PRELIS Examples

• Multilevel, Complex Survey, MGLIM and MVA Examples

FAQs for LISREL 11 and 12

Can I still use PSF files as input in LISREL 11 and LISREL 12?
No. However, a PSF can be renamed to an LSF and the resulting LSF can be opened in the LISREL GUI. However, before using in a syntax file, it must be saved as LISREL 11/12 LSF. Here is how to do it.

Can I use a LISREL 9 or LISREL 10 LSF in LISREL 11 and LISREL 12?
Yes.

Can I use matrix files in LISREL 11 and LISREL 12?
Yes, if the matrix files have previously been computed. Otherwise, we recommend using a LISREL 11/12 LSF so that the matrices can be generated by LISREL.

Are LISREL 9 and LISREL 10 syntax files compatible with LISREL 11 and LISREL 12?
Yes.

Can a variable name include, for example, a hyphen (-)?
Yes, if the variable name is specified with quotes. Examples are ‘VAR1*VAR11’,
‘soc – mobility’, ‘year#1:year#3’, etc.

Are variable names case sensitive?
Yes, they are. Using the name ‘Mathematics’ when the actual name in the LSF file is ‘mathematics’ will cause the program to terminate prematurely with an error message.

How do I turn an 8-character LSF file into a 16-character LSF file?
Here is an example of how to turn an existing LSF file into one that can accommodate longer variables names.

Where do I find test examples for LISREL 11 and LISREL 12?
LISREL 11 and 12 has a revised example folder structure. All examples on the Examples page refer to this structure. The revised set of examples can be downloaded here.

Technical documents

Documents discussing various theoretical aspects are listed. All these are available as PDF files and may be accessed by clicking on the appropriate link.

General information:

• Types of variables

• Types of moment matrices

• Types of correlation matrices

• The general LISREL model

• The extended LISREL model

• Methods of estimation

• Producing weight matrices and fit functions

• Problems with the analysis of correlation matrices

• Model assessment and modification

• Standardized solutions and direct, indirect, and total effects

• Threshold estimates

• Bootstrap estimates

• Imputation of missing values

• Homogeneity tests for categorical variables

• Robust standard errors and chi-squares

• Formulas for skewness and kurtosis

• Simulation with PRELIS and LISREL

• Confidence interval estimates

• Standard error estimates for standardized solutions

Continuous variable data based on a simple random sample:

• Full Information Maximum Likelihood (FIML) for Data with Missing Values

• Multiple Imputation for Data with Missing Values

• Latent Variable Scores

• Standardized Coefficients

• Equal t-values (complete example)

• The Interpretation of R2

• The Interpretation of R2 Revisited

• MINRES Exploratory Factor Analysis

• The Evaluation of Scale Reliability

• Scale Reliability for Maxima

Complete ordinal variable data based on a simple random sample:

• CFA, Structural and MIMIC Models

• LISREL Submodel 3

Complete censored variable data based on a simple random sample:

• Univariate Censored Regression

• Censored Variables and Censored Regression

• Multivariate Censored Regression

Two-stage multiple imputation SEM:

• Syntax for two stage multiple imputation SEM

• Two-stage multiple imputation SEM for continuous variables

• Two-stage multiple imputation SEM for ordinal variables

• Two-stage multiple imputation SEM for mixed correlations

Other:

• Multilevel structural equation modeling

• Multilevel nonlinear modeling

• Multilevel modeling with weights

• Structure Coefficients

• Notes by K.G. Jöreskog on ordinal data analysis in LISREL