Skip to main content

Table 8 Posterior medians and 95 per cent posterior credible intervals for the application of the dependent and independent models to simulated dependent and independent data (two-step informative priors for sensitivities alone were assigned (see Table 5 ))

From: A two-stage Bayesian method for estimating accuracy and disease prevalence for two dependent dichotomous screening tests when the status of individuals who are negative on both tests is unverified

 

Dependent data

Independent data

Dependent model

Independent model

Dependent model

Independent model

π = 0.10

0.0963 (0.0830,0.1151)

0.1184 (0.1088,0.1277)*

0.1030 (0.0919,0.1162)

0.1000 (0.0900,0.1107)

Se 1  = 0.70

0.6985 (0.6048,0.7960)

0.7971 (0.7841,0.7999)*

0.6558 (0.6028,0.7847)

0.6979 (0.6068,0.7940)

Se 2  = 0.80

0.7935 (0.7044,0.8950)

0.8965 (0.8818,0.8999)*

0.7864 (0.7030,0.8942)

0.7994 (0.7057,0.8942)

Sp 1  = 0.80

0.7978 (0.7775,0.8196)

0.8866 (0.8700,0.9028)*

0.7948 (0.7740,0.8156)

0.8002 (0.7801,0.8205)

Sp 2  = 0.70

0.6981 (0.6792,0.7164)

0.7677 (0.7511,0.7846)*

0.6966 (0.6764,0.7170)

0.6992 (0.6797,0.7191)

pD

3.87

3.08

3.87

3.38

DIC

58.63

323.08

58.63

58.76

  1. *: incorrect statistical inference.