Skip to main content

Table 2 Odds ratios and 95% confidence/credible intervals for the three comparisons from the considered models and priors in the first illustrative example on hepatitis C treatments for achieving sustained virological response (SVR)

From: Modelling heterogeneity variances in multiple treatment comparison meta-analysis – Are informative priors the better solution?

Model

PEG-2A+RBV vs INF+RBV

PEG-2B+RBV vs INF+RBV

PEG-2B+RBV vs PEG-2A+RBV

Random-effects pair wise meta-analysis

   

Frequentist (DerSimonian-Laird)

3.63(1.51-8.73)

1.30(1.11-1.52)

1.38(1.07-1.79)

Frequentist (Hartung-Makimbi)

3.60(1.56-8.34)

1.35(1.11-1.64)

1.38(0.36-3.24)

Bayesian (weakly informative)

NA*

1.36(1.10-1.73)

1.38(0.94-2.22)

Bayesian (frequentis informed)

NA*

1.30(1.11-1.55)

1.40(0.86-2.47)

Bayesian (empirically informed)

NA*

1.36(1.10-1.74)

1.38(1.02-1.99)

Random-effects MTC models

   

Weakly informed variance models

   

Homogeneous variance model

2.42(1.75-3.60)

1.53(1.19-2.03)

1.58(1.18-2.26)

  Unrestricted variances

2.11(1.40-3.57)

1.38(1.13-1.79)

1.50(1.06-2.53)

  Exchangeable variances*

2.17(1.48-3.43)

1.40(1.15-1.79)

1.53(1.11-2.36)

  Consistency variances structure

2.39(1.63-3.80)

1.42(1.16-1.86)

1.67(1.17-2.68)

Moderately informed variance models

   

  Frequentist informed priors

2.04(1.45-2.93)

1.38(1.15-1.69)

1.46(1.12-2.05)

  Empirically informed priors

2.23(1.54-3.40)

1.44(1.16-1.83)

1.54(1.13-2.29)

  1. * The MCMC simulation did not converge for the log odds ratio parameter (within the first 1.000.000 runs), and thus did not produce meaningful results.
  2. Abbreviations: PEG-2A (Peginterferon-2a); PEG-2B (Peginterferon-2b); INF (Interferon), RBV (Ribavirin).