Table 6.
Robust standard errors are shown in parentheses
The dotted/shaded column represents the best-fit model based on the lowest AIC criterion
AIC Akaike Information Criterion, BIC Bayesian Information Criterion, GLM generalized linear model
***p < 0.01, **p < 0.05, *p < 0.1
aGLM regression does not produce a regular R2; calculated as McFadden’s Pseudo R2 = (1 − LLM/LL0)