Table 3 Comparison of log-binomial and robust Poisson methods for analysis of death penalty associated with covariates*
Independent variableLog prevalence ratio estimate† (SE)p Value
Log-binomialRobust PoissonLog-binomialRobust Poisson
Black defendant0.3152 (0.1367)0.5935 (0.1992)0.02240.0029
White victim0.1219 (0.1078)0.3173 (0.2061)0.22880.1238
Serious−0.0010 (0.0174)0.0023 (0.0352)0.93050.9475
Culpability1.8062 (0.2750)1.9223 (0.4453)<0.001<0.001
Culpability squared−0.2006 (0.0308)−0.2158 (0.0624)<0.001<0.001
  • *Wald tests were used for the robust Poisson method, and likelihood ratio tests were used for the log-binomial method. The latter were obtained by fitting a model without the effect being tested, and calculating minus twice the difference in log likelihoods to get a χ2 test statistic and p value. In case the log-binomial did not converge, the COPY method approximation was used.

  • †The intercept estimate was −4.4445 for the log-binomial method and −4.9193 for the robust Poisson method. Of the 147 probability estimates, five were greater than unity for the robust Poisson method, and the largest was 1.28.