Skip to main content

Table 3 Results of the association parameter α obtained from the baseline Cox model, the TVCM and the joint model fitted to data generated considering the linear marker trajectory (scenario 2 of Table 1) with 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), asymptotic standard error (ASE), bias, 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

α=0.3

α=0.6

σε

Model

Est

ASE

Bias

CP

Est

ASE

%Bias

CP

Est

ASE

%Bias

CP

 

Cox.baseline

0.000

0.060

0.000

95

0.254

0.056

-15

86

0.545

0.059

-9.2

83

0.1

TVCM(1x/week)

-0.003

0.060

-0.003

96

0.293

0.058

-2.3

95

0.582

0.061

-3.0

93

 

TVCM(4x/week)

-0.001

0.060

-0.001

95

0.298

0.059

-0.7

94

0.594

0.062

-1.0

94

 

joint model

-0.003

0.059

-0.003

96

0.301

0.058

0.3

95

0.604

0.061

0.7

94

 

Cox.baseline

0.000

0.058

0.000

96

0.240

0.054

-20

79

0.508

0.057

-15

62

0.3

TVCM(1x/week)

-0.003

0.058

-0.003

96

0.275

0.057

-8.3

92

0.541

0.059

-9.8

83

 

TVCM(4x/week)

-0.001

0.058

-0.001

95

0.279

0.057

-7.0

92

0.550

0.059

-8.3

86

 

joint model

-0.003

0.060

-0.003

95

0.301

0.059

0.3

95

0.604

0.064

0.7

94

 

Cox.baseline

0.000

0.055

0.000

96

0.216

0.051

-28

61

0.449

0.053

-25

23

0.5

TVCM(1x/week)

-0.003

0.055

-0.003

96

0.244

0.053

-19

80

0.474

0.055

-21

35

 

TVCM(4x/week)

-0.002

0.055

-0.002

95

0.247

0.054

-18

84

0.480

0.055

-20

40

 

joint model

-0.004

0.062

-0.004

95

0.301

0.062

0.3

95

0.606

0.069

1.0

94