Considering time-interaction terms using parametric survival models for interval-censoring data

Abstract

Background: Many of the variables which are investigated in survival research are time-invariant, i.e. their values do not change over time. But their effects, may yet vary over time. Thus, the change in behavior that occurs over time needs to be included in the analysis. This can be done by adding time-interaction terms to the model.

Method: In this research, a parametric survival model, which is capable of evaluating the effects of time-dependent variables, was applied for interval-censored data such that the time to invariant variables interaction terms were considered as time-dependent variables.

Results: Using a practical example, the results of the study show that this model can alter the interpretations regarding the effects of exploratory variables.

Conclusion: when dealing with fixed variables whose effects change over time, the researcher can incorporate their interaction effect with time, and treat them as time-dependent variables and obtain appropriate inferences.