Skip to main content

Table 2 Results on the association parameter α obtained from the baseline Cox model, the TVCM and the joint model fitted to data generated considering a constant biomarker (scenario 1 of Table 1), α∈(0,0.3,0.6) and σε∈(0.1,0.3,0.5) with CV ∈(3.1%,9.4%,15.6%). Mean of the maximum likelihood estimates (Est), empirical Monte Carlo standard error (ESE), asymptotic standard error (ASE), percentage bias (%Bias) and 95% coverage probabilities (CP) are shown

From: Joint model robustness compared with the time-varying covariate Cox model to evaluate the association between a longitudinal marker and a time-to-event endpoint

  

α=0.3

α=0.6

σε

Model

Est

ESE

ASE

%Bias

CP

Est

ESE

ASE

%Bias

CP

 

Cox.baseline

0.299

0.056

0.056

-0.3

95

0.598

0.060

0.060

-0.3

94

0.1

TVCM(1x/week)

0.299

0.056

0.056

-0.3

95

0.598

0.060

0.060

-0.3

94

 

joint model

0.302

0.055

0.056

0.7

95

0.605

0.059

0.059

0.8

94

 

Cox.baseline

0.283

0.054

0.055

-5.7

94

0.557

0.059

0.058

-7.2

87

0.3

TVCM(1x/week)

0.282

0.054

0.055

-6.0

94

0.557

0.057

0.058

-7.2

88

 

joint model

0.302

0.057

0.057

0.7

95

0.606

0.062

0.061

1.0

95

 

Cox.baseline

0.254

0.052

0.052

-15

85

0.489

0.056

0.054

-18

45

0.5

TVCM(1x/week)

0.252

0.051

0.052

-16

84

0.489

0.053

0.054

-18

46

 

joint model

0.302

0.059

0.058

0.7

95

0.607

0.068

0.066

1.2

94