Understand and calculate AIC, BIC, deviance, and R-squared.

Free CAS MAS-I (Modern Actuarial Statistics I) lesson in Extended Linear Models. 14 min read, ~2,062 words.

AIC; BIC. Lower is better. BIC penalizes parameters harder once (because ). Scaled deviance measures lack of fit versus the saturated model. Unscaled deviance uses the dispersion. Nested GLMs: difference in scaled deviance where is the parameter-count gap. This is the GLM analog of the partial -test. for OLS only...