Skip to main content

Table 3 Posterior mean hazard ratio estimates from separate survival models for competing risk data

From: Joint modeling of multivariate longitudinal data and the dropout process in a competing risk setting: application to ICU data

  

Cause specific hazards

Subdistribution hazards

ICU DEATHS

No deaths/No pts

HR

95%CI

SHR

95%CI

Treatment group

     

A

191/703

1

 

1

 

B

182/698

1.04

(0.85,1.27)

1.03

(0.85,1.26)

Age

     

<63 years

151/717

1

 

1

 

≥63 years

222/684

1.40

(1.14,1.73)*

1.58

(1.28,1.94)*

Gender

     

Female

150/547

1

 

1

 

Male

223/854

0.90

(0.73,1.10)

0.95

(0.78,1.16)

Entry mode

     

Other

185/737

1

 

1

 

Sepsis

188/664

0.95

(0.77,1.16)

1.09

(0.89,1.33)

DISCHARGE ALIVE

No events/No pts

    

Treatment group

     

A

429/698

1

 

1

 

B

431/703

0.99

(0.87,1.13)

1.00

0.87,1.14)

Age

     

<63 years

493/717

1

 

1

(0.59,0.77)*

≥63 years Gender

367/684

0.71

(0.62,0.81)*

0.67

 

Female

330/547

1

 

1

 

Male

530/854

0.92

(0.80,1.06)

0.95

(0.83,1.09)

Entry mode

     

Other

486/737

1

 

1

 

Sepsis

374/664

0.72

(0.63,0.83)*

0.76

(0.67,0.87)*

  1. Posterior mean hazard ratio estimates from separate survival models for competing risk data, namely, the cause-specific hazard (HR) model and the sub-distribution hazard (SHR) model. * indicates a p-value < 0.05 based on Wald tests.
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us