In order to estimate the DTSA models in a latent variable framework, the raw data were prepared as outlined by Muthen & Masyn (2005). Since there was considerable age heterogeneity at each measurement wave, the hazard/survival curves were modeled as a function of the age of first drink, rather than of measurement occasion. A total of 12 binary time-specific event indicators were constructed to reflect yearly intervals between the youngest reported age of alcohol onset (12 years) and the oldest reported age of alcohol onset (22 years) for this subsample. The subject was considered to have experienced the event of interest at the age they reported drinking at least one full drink of alcohol for the first time, designated by a “1” score on the binary time-specific event indicators for the corresponding age; prior ages were scored “0” to reflect no event, and subsequent ages were treated as missing due to having experienced the event. Right-censoring occurred when a subject did not report alcohol onset by their most recent assessment. Such subjects would have “0” scores for all ages that
