Skip to main content

Table 3 Approaches of Competing Risks Flexible Parametric Models

From: Methods of competing risks flexible parametric modeling for estimation of the risk of the first disease among HIV infected men

ModelMeasures of associationsWhat is the model useful for?How to model?AdvantagesDisadvantagesWhich Stata commands?
Cause-specific hazard flexible parametric modelhazardEtiological questions: which covariates have a causal effect on the occurrence of the eventCSHFPMEasy to perform (on the original data) and interpret, using the standard FPMFitting separate models for each eventstpm2
   Unified CSHFPMFitting one model instead of separate models, using the standard FPM, Ability to handle shared covariate effectsConsidering the same knot positions for all events, complex implementation (on the stacked data), Potential convergence problemsStratified stpm2
Cause-specific subdistribution hazard flexible parametric modelSubdistribution hazard and cumulative incidence function (risk)Prognosis questions: What fraction of patients are at risk to experience the event at a particular timeSDHFPM1Fitting a separate model for the event of interest, using the standard FPMIntensive computation (not ideal for large data sets), no constraint on the sum of CIFsstcrprep and stpm2
   SDHFPM2Fitting a unified model for all events (when the focus is on all events), Easy to perform (on the original data) and interpret, Less computation (ideal for large data sets)convergence problems for small sample sizes, no constraint on the sum of CIFsstpm2cr