Closed mvanrongen closed 5 months ago
Uses a slightly different method than dividing the deviance by the residual degrees of freedom. Instead, it's based on Gelman, A., and Hill, J. (2007). Data analysis using regression and multilevel/hierarchical models. Cambridge; New York: Cambridge University Press.
Reproducible outcome when manually calculating using the same method, so verified.
When running
check_overdispersion(glm_gal)
the outcome is different to manually calculating the dispersion parameter usingglm_gal$deviance / glm_gal$df.residual
.