Skip to main content

Table 2 Parameter estimates from the alternative MTC synthesis models

From: Network meta-analysis of (individual patient) time to event data alongside (aggregate) count data

 

Model A

Model B

Model C1

Model C2

Model D

Hazard ratios

HR

Median (95% CrI)

P

HR

Median (95% CrI)

P

HR

Median (95% CrI)

P

HR

Median (95% CrI)

P

HR

Median (95% CrI)

P

Treatment effects

4LB

—

—

5.5

—

—

1.4

—

—

6.2

—

—

5.7

—

—

4.3

SSB

0.88

(0.76, 1.03)

0.4

0.96

(0.77, 1.22)

0.6

0.89

(0.77, 1.04)

0.6

0.89

(0.77, 1.04)

0.6

0.84

(0.70, 0.99)

0.2

HH

1.05

(0.85, 1.29)

16.1

1.63

(0.76, 3.53)

59.2

1.03

(0.83, 1.27)

14.9

1.03

(0.84, 1.27)

15.0

1.03

(0.84, 1.28)

11.1

ZINC

0.77

(0.41, 1.42)

6.2

0.78

(0.37, 1.62)

2.8

0.78

(0.41, 1.44)

6.5

0.78

(0.41, 1.43)

6.7

0.75

(0.03, 29.49)

17.5

2LB

1.40

(0.65, 3.05)

71.9

1.39

(0.62, 3.30)

36.0

1.38

(0.66, 3.05)

71.8

1.38

(0.63, 3.04)

72.0

1.59

(0.61, 5.34)

67.0

Baseline characteristics

Log area

0.71

(0.66, 0.76)

—

0.71

(0.66, 0.76)

—

0.70

(0.65, 0.75)

—

0.70

(0.65, 0.75)

—

0.71

(0.65, 0.76)

—

Log duration

0.92

(0.90, 0.94)

—

0.92

(0.90, 0.94)

—

0.92

(0.91, 0.94)

—

0.93

(0.91, 0.94)

—

0.92

(0.90, 0.94)

—

Difficulty in walking

0.71

(0.60, 0.85)

—

0.73

(0.60, 0.86)

—

0.72

(0.60, 0.85)

—

0.72

(0.60, 0.85)

—

0.71

(0.60, 0.80)

—

Immobile

0.67

(0.23, 1.52)

—

0.66

(0.23, 1.51)

—

0.72

(0.24, 1.65)

—

0.72

(0.25, 1.67)

—

0.68

(0.24, 1.59)

—

Interactions

Log area

—

—

—

—

—

—

—

—

—

—

—

—

1.00

(0.97, 1.10)

—

Log duration

—

—

—

—

—

—

—

—

—

—

—

—

1.00

(0.99, 1.00)

—

 

Btw-centre SD

0.04

(0.01, 0.13)

—

0.05

(0.01, 0.13)

—

0.05

(0.01, 0.15)

—

0.05

(0.01, 0.15)

—

  

—

 

Btw-study SD

—

—

—

0.13

(0.01, 0.51)

—

—

—

—

—

—

—

—

—

—

 

λ

1.07

(1.01, 1.13)

—

1.07

(1.01, 1.14)

λ 1 **

0.93

(0.86, 1.01)

λ 1

0.93

(0.86, 1.01)

—

1.07

(1.01, 1.14)

—

       

λ 2

1.27

(1.17, 1.38)

λ 2 **

1.27

(1.17, 1.38)

    
 

DIC

5396.2

5396.2

5371.2

5371.5

5377.4

  1. Model A – Fixed-effects NMA, Weibull model of IPD+AD; model B – Random-effects NMA, Weibull model of IPD+AD; model C1 - Fixed-effects NMA, Weibull model of IPD+AD, shape parameter derived from IPD study 1 only; model C2 - Fixed-effects NMA, Weibull model of IPD+AD, shape parameter derived from IPD study 2 only; model D - Fixed-effects NMA, Weibull model of IPD+AD, considering 2 treatment-effect modifiers.
  2. **Shape parameter used in the synthesis model section for summary data.
  3. 4LB = four layer bandage; SSB = Short stretch bandage; HH = two layer hosiery; 2LB = two layer bandage.
  4. HR = hazard ratios; CrI = credibility interval; SD = standard deviation; P = probability of being the best treatment choice in terms of healing (%); DIC – deviance information criteria.
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us