An unconditional discrete-time survival model was then fitted for the remission of AUDs across adulthood in the probands using only the binary (e.g., remission present or not) time-specific (e.g., T20) event indicators. The estimated hazard function captured the conditional probability that an individual would no longer meet criteria for an AUD in a specific age interval given that he did not remit in an earlier interval, and this was used to calculate the survival function over time. Figure 1 illustrates a steep increase in the rates of AUD remission from T10 to T15, with a lower rate of remission onset from T15 through T30. The constant hazard assumption was next evaluated to assess whether the hazard rate varied significantly across adulthood. The unconditional hazard model (with time-varying hazard rates) was found to significantly improve fit compared to a model that constrained the hazard rate to equality for initial remission (χ2(3) = 13.36, p<.01) and for sustained remission (χ2(3) = 10.73, p<.05). Thus, the constant baseline hazard assumption was rejected and the hazard function was allowed to vary across age intervals in all subsequent models for both outcomes.
