Mplus Users Guide v6.. - Muthén & Muthén

Examples: Mixture Modeling With Cross-Sectional Datac2 to indicate that they are allowed to be a member of either class andthat their class membership is estimated.In the overall model, the first ON statement describes the linearregression of y on the covariate x1 and the treatment dummy variable x2.The intercept and residual variance of y are estimated as the default.The second ON statement describes the multinomial logistic regressionof the categorical latent variable c on the covariate x1 when comparingclass 1 to class 2. The intercept in the regression of c on x1 is estimatedas the default.In the model for class 1, a starting value of zero is given for the interceptof y as the default. The residual variance of y is specified to relax thedefault across class equality constraint. The ON statement describes thelinear regression of y on x2 where the slope is fixed at zero. This isdone because non-compliers do not receive treatment. In the model forclass 2, a starting value of .5 is given for the intercept of y. The residualvariance of y is specified to relax the default across class equalityconstraint. The regression of y ON x2, which represents the CACEtreatment effect, is not fixed at zero for class 2. The default estimatorfor this type of analysis is maximum likelihood with robust standarderrors. The ESTIMATOR option of the ANALYSIS command can beused to select a different estimator. An explanation of the othercommands can be found in Example 7.1.EXAMPLE 7.24: MIXTURE RANDOMIZED TRIALSMODELING USING CACE ESTIMATION WITH MISSINGDATA ON THE LATENT CLASS INDICATORTITLE: this is an example of mixture randomizedtrials modeling using CACE estimation withmissing data on the latent class indicatorDATA: FILE IS ex7.24.dat;VARIABLE: NAMES ARE u y x1 x2;CLASSES = c (2);CATEGORICAL = u;MISSING = u (999);ANALYSIS: TYPE = MIXTURE;181