Skip to main content

Table 1 Results of Bayesian geostatistical models to predict prevalence of P. vivax and P. falciparum for Tanna Island, 2008.

From: Baseline spatial distribution of malaria prior to an elimination programme in Vanuatu

  Coefficient, posterior mean Odds ratio, posterior mean (95% Bayes credible intervals#) DIC
Model of P. vivax with distance to coastline fixed effect    
α (intercept) -4.680 (-5.317- -4.137)   
Distance from coastline (OR per 1 km) -0.690 (-1.151- -0.242) 0.730 (0.591-0.895)  
Φ (rate of decay of spatial correlation)* 251.5(51.26-569.4)   
σ2 (variance of geostatistical random effect)** 0.214 (0.056 - 0.624)   
DIC    306.9
Model of P. vivax with elevation fixed effect    
α (intercept) -4.611 (-5.327 - -3.931)   
Elevation (OR per 100 m) -0.547 (-0.992- 0.115) 0.654 (0.468, 0.917)  
Φ (rate of decay of spatial correlation)* 167.8 (33.71, 461.2)   
σ2 (variance of geostatistical random effect)** 2.471 (1.271, 4.304)   
DIC    308.9
Model of P. falciparum with distance to coastline fixed effect    
α -5.238 (-6.027 - -4.625)   
Distance from coastline (OR per 1 km) -0.101 (-0.534 - 0.334) 0.955 (0.783, 1.165)  
Φ 289.5 (51.61 - 575.4)   
σ 2 0.584 (0.057 - 4.713)   
DIC    219.5
Model of P. falciparum with elevation fixed effect    
α -5.129 (-5.976 - -4.416)   
Elevation (OR per 100 m) -0.207 (-0.673 - 0.146) 0.864 (0.603, 1.149)  
Φ 238.2 (53.28 - 478.9)   
σ 2 1.753 (0.4521 - 4.079)   
DIC    218.9
  1. * The unit is change in spatial autocorrelation per decimal degree. A lower Φ indicates that spatial correlation occurs over longer distances (i.e. spatial clusters are larger).
  2. ** A higher variance indicates a greater tendency toward spatial clustering.
  3. # Bayes credible intervals can be interpreted as having a similar meaning to confidence intervals used in frequentist statistics.