Mplus Users Guide v6.. - Muthén & Muthén

Examples: Mixture Modeling With Longitudinal Dataestimation is specified by using the ESTIMATOR option of theANALYSIS command. Bootstrap standard errors are obtained by usingthe BOOTSTRAP option of the ANALYSIS command. Bootstrapconfidence intervals are obtained by using the BOOTSTRAP option ofthe ANALYSIS command in conjunction with the CINTERVAL optionof the OUTPUT command. The MODEL TEST command is used to testlinear restrictions on the parameters in the MODEL and MODELCONSTRAINT commands using the Wald chi-square test. TheAUXILIARY option is used to test the equality of means across latentclasses using posterior probability-based multiple imputations.Graphical displays of observed data and analysis results can be obtainedusing the PLOT command in conjunction with a post-processinggraphics module. The PLOT command provides histograms,scatterplots, plots of individual observed and estimated values, plots ofsample and estimated means and proportions/probabilities, and plots ofestimated probabilities for a categorical latent variable as a function ofits covariates. These are available for the total sample, by group, byclass, and adjusted for covariates. The PLOT command includesa display showing a set of descriptive statistics for each variable. Thegraphical displays can be edited and exported as a DIB, EMF, or JPEGfile. In addition, the data for each graphical display can be saved in anexternal file for use by another graphics program.Following is the set of GMM examples included in this chapter:• 8.1: GMM for a continuous outcome using automatic starting valuesand random starts• 8.2: GMM for a continuous outcome using user-specified startingvalues and random starts• 8.3: GMM for a censored outcome using a censored model withautomatic starting values and random starts*• 8.4: GMM for a categorical outcome using automatic starting valuesand random starts*• 8.5: GMM for a count outcome using a zero-inflated Poisson modeland a negative binomial model with automatic starting values andrandom starts*• 8.6: GMM with a categorical distal outcome using automaticstarting values and random starts• 8.7: A sequential process GMM for continuous outcomes with twocategorical latent variables199