Skip to main content

Advertisement

Table 3 Sensitivity analysis in the estimated parameters of fixed effects with different hyperparameters (a, b) in the prior of variance parameters

From: Explaining large mortality differences between adjacent counties: a cross-sectional study

  a = 0.1, b = 0.1 a = 0.01, b = 0.01 a = 0.001, b = 0.001 a = 0.0001, b = 0.0001
Variable Estimate 95 % CI Estimate 95 % CI Estimate 95 % CI Estimate 95 % CI
Intercept −1.05 −14.36 10.62 −1.34 −12.54 8.85 −1.06 −12.88 10.05 −1.64 −12.32 8.05
 ΔPopulation unable to obtain medical care because of cost 1.93 −1.04 4.86 2.60 0.59 4.57 2.16 −0.17 4.46 2.75 0.80 4.74
 ΔHospital discharge rate 1.28 0.33 2.23 1.03 0.66 1.38 1.11 0.60 1.65 0.99 0.68 1.32
 ΔPopulation in fair or poor health 1.86 −0.49 4.36 2.93 1.26 4.59 2.59 0.57 4.59 3.14 1.40 4.74
 ΔPopulation with high blood pressure 6.08 3.50 8.64 4.75 2.94 6.47 5.22 3.20 7.16 4.57 2.96 6.23
 ΔPopulation below federal poverty level 6.65 4.05 9.14 6.09 4.38 7.97 6.18 4.20 8.22 6.08 4.34 7.81
  1. Abbreviations: CI credible interval
  2. Δ signifies the difference between adjacent counties