Mplus Users Guide v6.. - Muthén & Muthén

Examples: Mixture Modeling With Longitudinal Datau1 u2 u3u4 u5 tcxIn this example, the continuous-time survival analysis model shown inthe picture above is estimated. This is a Cox regression mixture modelsimilar to the model of Larsen (2004) as discussed in Asparouhov et al.(2006). The profile likelihood method is used for estimation.The SURVIVAL option is used to identify the variables that containinformation about time to event and to provide information about thetime intervals in the baseline hazard function to be used in the analysis.The SURVIVAL option must be used in conjunction with theTIMECENSORED option. In this example, t is the variable thatcontains time-to-event information. By specifying the keyword ALL inparenthesis following the time-to-event variable, the time intervals aretaken from the data. The TIMECENSORED option is used to identifythe variables that contain information about right censoring. In thisexample, the variable is named tc. The information in parenthesesspecifies that the value zero represents no censoring and the value onerepresents right censoring. This is the default. The BASEHAZARDoption of the ANALYSIS command is used with continuous-timesurvival analysis to specify if a non-parametric or a parametric baselinehazard function is used in the estimation of the model. The setting OFFspecifies that a non-parametric baseline hazard function is used. This isthe default.In the overall model, the first ON statement describes the loglinearregression of the time-to-event variable t on the covariate x. The second231