Skip to main content

Table 4 Variance parameter estimates

From: Confounding and missing data in cost-effectiveness analysis: comparing different methods

 

DSQ < 4

DSQ ≥ 4

θ a

E [ θ | d ] b b

95% CI b

E [ θ | d ] b b

95% CI b

σ E , · , 1 2

0.10

0.07

0.14

0.13

0.09

0.19

σ E , · , 2 2

0.09

0.06

0.12

0.12

0.09

0.18

σ E , · , 3 2

0.07

0.05

0.11

0.09

0.06

0.13

σ E , · , 4 2

0.10

0.06

0.16

0.17

0.1

0.26

τ P,·,1

12.15

8.28

17.19

8.09

5.55

11.37

τ P,·,2

6.07

4.06

8.51

3.79

2.61

5.3

τ P,·,3

4.12

2.57

6.08

4.67

3.01

6.82

τ P,·,4

2.07

1.21

3.13

1.95

1.16

2.91

  1. The parameters controlling the variance of effectiveness and the dispersion of the positive costs in the Bayesian model.
  2. aParameters σ E , · , · 2 control the variance of the effectiveness measure, and parameters τ ·,· (inverse of variance-to-mean ratio) the dispersion of the positive costs in the Bayesian model. Parameter θ is a generic notation representing one of the parameters σ E , · , · 2 or τ ·,·.
  3. bThe point estimates are posterior expectations E[θ|d] and also 95% credible intervals (CI) are presented