Skip to main content

Table 1 Possible relations between transitions 1 → 3 and 2 → 3 if approach J is used

From: Multi-state model for studying an intermediate event using time-dependent covariates: application to breast cancer

J.I

λ 23(t,d)=λ 13(t)

The hazard rate remains the same

J.II

λ 23(t,d)=c·λ 13(t)

The hazard rate changes by

  

the factor c (constant)

J.III.1

λ 23(t,d)=c(d)·λ 13(t)

c depends on d, the

  

time of ILRR

J.III.2

λ 23(t,d)=c(t - d)·λ 13(t)

c depends on t - d, the

  

time since ILRR

J.IV

λ 23(t,d)=c(d,t - d)·λ 13(t)

c depends on d as well as

  

on t - d the time since ILRR