Treat everyone with sincerity, they will certainly appear likeable and friendly. Survival Analysis
Parametric Regression Models Survival Analysis Parametric Regression Models Survival Analysis
Abbreviated Outline Proportional hazards (PH) modeling Accelerated failure time (AFT) modeling Diagnosis for models/ model selection Survival Analysis
Notation Y: survival time X: covariate vector hx(y): the hazard function of Y given X Sx(y): the survival function of Y given X Yx: Y given X Survival Analysis
Proportional Hazards Model hx(y) = h0(y)*g(X) Hazard function of Y given X Baseline hazard function A positive function Common choice of g(x): Survival Analysis
Accelerated Failure Times Model Yx * g(X) = Y0 Sx(y) = S0(yg(X)) Baseline survival function Common choice of g(x): Survival Analysis
Notes AFT model = PH model if and only if the survival time is Weibull distributed. A more robust (semi-parametric) method has been developed for the PH model and so fitting the parametric PH model will not be demonstrated here. Survival Analysis
Several AFT Models Weibull AFT model Lognormal AFT model Survival Analysis
Model Diagnosis SAS reference: SAS textbook Chapter 4 Checking the parametric model for Y Checking the AFT assumption Residual analysis Survival Analysis
Model Diagnosis Checking the model for Y: If no censored observations, use Q-Q plots. If with censored observations, compare to the K-M estimates. Survival Analysis
Graphical Diagnosis for Parametric Models on Y Exponential model Weibull model Lognormal model Log logistic model (exercise) Note: these methods do not take covariates into account; must be done by groups Survival Analysis
Model Diagnosis Checking the AFT model: Fit Kaplan-Meier estimator to each group separately Compute a sequence of percentiles for each group Draw the Q-Q plot of one group vs. another group “almost linear” implies AFT model Survival Analysis
Final Model Selection Parametric model comparisons: Use likelihood ratio test (See SAS textbook p.89 for details and examples) Use AIC (See Klein Sec. 12.4) Survival Analysis
Residual Analysis Cox-Snell residual: and are i.i.d. exp(1). Survival Analysis
Residual Analysis See SAS textbook p.95 for SAS code. The residual analysis is NOT sensitive to the difference in model fit. Survival Analysis
Summary Fit AFT model including all covariates based on the Lognormal, Weibull and Generalized Gamma models for Y (totally 3 models) Use LR tests/AIC to determine your initial model (either lognormal or weibull) Do backward model selection and residual analysis Survival Analysis