What are the system requirements for LISREL for Windows?
_____________________________________________________________
LISREL for Windows for Windows requires Windows 95, Windows 98, Windows-ME, Windows 2000 or Windows XP.
_____________________________________________________________
How do I know which version of LISREL I am running?
_____________________________________________________________
Use the About LISREL option on the Help menu to load the About LISREL dialog box.
_____________________________________________________________
Why are my syntax and/or output files empty?
_____________________________________________________________
If this occurs immediately after installation, restart Windows and try again.
This could happen if the complete filename consist of more than 192 characters.
_____________________________________________________________
How do I obtain the latest version of LISREL for Windows?
_____________________________________________________________
Download the latest patch file(s) from our website www.ssicentral.com and save it to the folder in which LISREL for Windows is installed.
Use the Run option from the Windows Start menu to run the patch file(s) from the folder in which LISREL for Windows is installed.
_____________________________________________________________
How can I test my installation?
_____________________________________________________________
Use the Open option on the File menu to load the Open dialog box.
Browse for the file EX1.LS8 in the LS8EX subfolder of the folder in which LISREL for Windows was installed.
Click on the Open button to open the text editor window for EX1.LS8.
Click on the Run LISREL toolbar icon to open the PTH window for EX1.PTH.
_____________________________________________________________
Why should I use LISREL for Windows?
_____________________________________________________________
Although LISREL 8.8 for Windows is primarily intended for Structural equation modeling for Sample Covariance Matrices, LISREL for Windows includes, amongst others, the following special features:
Statistical Methods for Complex Survey Data
Statistical Methods for Data with Missing Values
Statistical Methods for Censored Variables
Statistical Methods for Ordinal and Categorical Variables
Statistical Methods for Correlation Matrices
Multilevel Structural Equation Modeling
Multilevel Linear and Nonlinear Modeling
Formal Inference-based Recursive Modeling (FIRM)
Exploratory Factor Analysis
Two Stage Least Squares Estimation
Latent Variable Scores
Factor Scores
Normal Scores
_____________________________________________________________
Which applications does LISREL for Windows include?
_____________________________________________________________
PRELIS is a 32-bit application that can transform data, compute moment matrices, compute asymptotic covariance matrices, impute missing data, compute factor scores, perform regression analyses and perform exploratory factor analyses.
LISREL is a 32-bit application for Structural equation modeling as well as Multilevel SEM.
MULTILEV is a 32-bit application for Multilevel Linear and Nonlinear Modeling.
CATFIRM is a 32-bit application for Formal Inference-based Recursive Modeling for categorical data.
CONFIRM is a 32-bit application for Formal Inference-based Recursive Modeling for continuous data.
SURVEYGLIM fits Generalized LInear Models (GLIMs) to data emanating from simple random and complex survey designs.
LISWIN32 is a 32-bit Windows application that allows the interactive execution (interface) of the six 32-bit applications of LISREL for Windows.
_____________________________________________________________
Which method of estimation should I use?
_____________________________________________________________
If the data are continuous and approximately follow a multivariate Normal distribution, then the Method of Maximum Likelihood is recommended.
If the data are continuous and approximately do not follow a multivariate Normal distribution and the sample size is not large, then the Robust Maximum Likelihood Method is recommended. This method will require an estimate of the asymptotic covariance matrix of the sample variances and covariances.
If the data are ordinal, categorical or mixed, then the Diagonally Weighted Least Squares (DWLS) method for Polychoric correlation matrices is recommended. This method will require an estimate of the asymptotic covariance matrix of the sample correlations.
_____________________________________________________________