LISREL 8.8
Introduction
LISREL offers an impressive array of facilities for data analysis, including indirect and total effects and their standard errors; direct specification of mean parameters; a Ridge Option for handling covariance and correlation matrices that are not positive-definitive; and modification indices for all iterative estimation methods.
LISREL 8.8 includes a number of new features.
Generalised Linear Models for complex survey data
The new SurveyGLIM module in LISREL 8.8 allows users to select from the multinomial, Bernoulli, binomial, Poisson, negative binomial, gamma, Gauss and inverse Gaussian sampling distributions.
Design weights in the LISREL Multilevel modeling module
Users can include sample design weights for the analysis of hierarchical linear models. This makes it possible to specify weights on levels 1, 2 or 3 of the hierarchy. Correct parameter estimates and robust standard errors are produced under complex sampling designs.
Sampling weights for SEM models when data is missing at random
In LISREL 8.7, it is possible to use design weights to fit SEM models to continuous data with missing values. A full information maximum likelihood method is used to obtain the correct parameter estimates and robust standard errors given the sampling weights.
Multivariate Censored Regression
LISREL’s univariate regression methods have been extended to allow for multivariate censored regression. In addition, the appropriate sample covariance matrix for a set of censored variables may be computed and used to fit structural equation models to censored data.
Goodness-of-fit statistics
LISREL 8.8 produces an additional file with the file extension “FTB” that contains a listing of these goodness-of-fit statistics based on all four chi-square test statistic values that LISREL 8.8 reports.
PRELIS
Included with LISREL is PRELIS, a pre-processor for LISREL which greatly improves and accelerates analysis of binary, categorical, ordinal, censored, continuous, and/or incomplete data. New features of PRELIS include: missing values on a variable that may be inputted by matching on other variables, new variables that may be created as functions of other variables, tests of univariate and multivariate normality that are obtained for all continuous variables and more.