Table 2. Model statistics from two spatio-temporal models evaluating striped skunk rabies incidence in Kansas, Nebraska in the Northern Plains, USA.
| Parameter | Partial model (1a) | Partial model (1b) | Covariate model |
|---|---|---|---|
| Random effect terms (Mean ± SD) £ | |||
| β0 | 0.35 ± 0.04 | 0.33 ± 0.04 | 0.28 ± 0.03 |
| ui | 0.04 ± 0.00 | 0.06 ± 0.02 | 0.02 ± 0.01 |
| vi | 0.18 ± 0.02 | 0.11 ± 0.01 | 0.08 ± 0.02 |
| γj | 0.23 ± 0.05 | 0.20 ± 0.05 | 0.21 ± 0.05 |
| Ψij | - | -0.03 ± 0.05 | - |
| Fixed effect covariates (Odds ratio, 95% Credible Intervals)¶ | |||
| β1 (% developed—low intensity areas) | - | - | 3.41 (2.01, 3.83) |
| β2 [Total edge contrast index (fragmentation)] | - | - | 1.70 (1.26, 2.81) |
| β3 (Diurnal temperature range) | - | - | 0.54 (0.27, 0.91) |
£ Mean and standard deviation correspond to the posterior estimates for the hyperparameters τu,τv,τγ, and τψ in the three Bayesian models present above.
¶ The odds ratio and credible intervals correspond to the median of the posterior predictive distributions of the covariate model.
β0 is intercept in all models, representing positive striped skunk rabies infection in all locations in all years, and ui and are vi random terms accounting for spatially structured variation in striped skunk rabies infection and unstructured heterogeneity in the data, respectively. γj and Ψij terms represent non-parametric time trend and spatio-temporal interactions, respectively. Information on the choice of priors for these terms are provided in the text.