Skip to main content

Table 4 Bayesian logistic regression model for the association of socio-economic, behavioural, climatic condition and spatially structured and unstructured random effect at the zone level with poor tuberculosis treatment outcomes in Ethiopia, 2015 to 2017

From: Mapping tuberculosis treatment outcomes in Ethiopia

Variables

Unstructured model

Structured model

Structured & unstructured model

Model without covariates

OR, Posterior

Mean (95%

CrI

OR, Posterior

Mean (95%

CrI

OR, Posterior

Mean (95%

CrI

 

Chat chewing

0.99 (0.98, 1.00)

0.99 (0.98, 1.00)

0.99 (0.98, 1.00)

–

Low wealth index

1.01 (1.00, 1.01)

1.01 (1.00, 1.01)

1.01 (1.00, 1.01)

–

Knowledge towards TB

1.02 (1.01, 1.03)

1.013 (1.00, 1.03)

1.02 (1.01, 1.03)

–

Mean temperature

1.15 (1.08, 1.21)

1.12 (1.045, 1.18)

1.14 (1.08, 1.20)

–

Constant (alpha)

−5.57 (−6.64, −4.39)

−5.04 (− 6.17, −3.74)

− 5.48 (− 6.51, − 4.37)

−2.11 (−2.14, −2.07)

Heterogeneity

 

 Unstructured variance

0.63 (0.53, 0.74)

–

0.24 (0.028, 0.83)

 

 Structured variance

–

1.264 (1.07, 1.50)

0.59 (0.42, 0.73)

1.57 (1.34, 1.84)

 DIC

746.0

764.5

752.0

760.8

  1. CrI credible interval, DIC deviance information criterion, OR odds ratio
  2. The boldface indicate statistically signficant variables