Skip to main content

Table 1 OR estimates and 95% confidence intervals from geometric and logistic regression models of physician visits for the German Socio-Economic Panel data

From: Odds ratios from logistic, geometric, Poisson, and negative binomial regression models

  Geometric Logistic Relative widthe
Covariate Estimate Interval Estimate Interval  
Post-reforma 0.87 (0.79, 0.96) 0.82 (0.68, 0.99) 57%
Bad healthb 3.13 (2.71, 3.63) 3.28 (2.24, 4.82) 36%
Education (10.5 - 12 years)c 1.09 (0.95, 1.24) 1.19 (0.94, 1.51) 50%
Education (HS graduate +)c 0.97 (0.84, 1.11) 1.32 (1.03, 1.70) 40%
Age (40 - 49 years)d 1.05 (0.93, 1.19) 0.92 (0.73, 1.16) 62%
Age (50 - 60 years)d 1.21 (1.05, 1.39) 0.99 (0.76, 1.29) 64%
Log household income 1.13 (0.99, 1.30) 1.26 (0.98, 1.62) 48%
  1. Reference category: a Pre-reform; b Good health; c 7 - 10 years of education; d Age 20–39 years e Geometric compared to logistic model