Additive Models2026-11-11additive‑modelsgamsmoothingpenalised‑least‑squaresirlscross‑validationgcvmgcvregressionstatisticsmath5806agenticAdditive models and generalised additive models from MATH5806: one smooth per predictor, a basis and a penalty for each, penalised least squares or penalised IRLS to fit, and GCV to choose the smoothing.