XiangdongGu / icensmis

Study Design and Data Analysis in the Presence of Error-Prone Diagnostic Tests and Self-Reported Outcomes
1 stars 0 forks source link

Issue-4: Proportional hazard test assumption #10

Open XiangdongGu opened 3 years ago

XiangdongGu commented 3 years ago

Test PH assumptions by adding interaction terms between time and covariates. See how it is achieved in other models like Cox models.

XiangdongGu commented 3 years ago

PH test can be achieved by adding interaction term with time, see book section 4.4.3 in book Modelling Survival Data in Medical Research by David Collett. Likelihood ratio test can be used to test the interaction term to infer whether the PH assumption is violated or not.

simdata3 <- datasim(N = 1000, blambda = 0.05, testtimes = 1:8, 
                    sensitivity = 0.7, specificity = 0.98, betas = c(0.5, 0.8, 1.0),
                    twogroup = NULL, pmiss = 0.3, design = "MCAR", negpred = 1)               

fit3 <- icmis(subject = ID, testtime = testtime, result = result,
              data = simdata3, sensitivity = 0.7, specificity= 0.98, 
              formula = ~cov1+cov2+cov3, negpred = 1)

fit3int <- icmis(subject = ID, testtime = testtime, result = result,
                 data = simdata3, sensitivity = 0.7, specificity= 0.98, 
                 formula = ~(cov1+cov2+cov3)*testtime - testtime, negpred = 1)

test_stat <- 2 * (fit3int$loglik - fit3$loglik)
pvalue <- pchisq(test_stat, 3, lower.tail=FALSE)
pvalue