Hi, summary(pres.gam) Family: gaussian Link function: identity Formula: prestige ~ s(income) + s(education) Parametric coefficients: ??????????? Estimate Std. Error t value Pr(>|t|)??? (Intercept)? 47.3276???? 0.6914?? 68.45?? <2e-16 *** --- Signif. codes:? 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 Approximate significance of smooth terms: ?????????????? edf Ref.df???? F? p-value??? s(income)??? 3.079? 3.813 12.18 8.03e-08 *** s(education) 3.005? 3.746 42.68? < 2e-16 *** --- Signif. codes:? 0 ?***? 0.001 ?**? 0.01 ?*? 0.05 ?.? 0.1 ? ? 1 R-sq.(adj) =?? 0.84?? Deviance explained =?? 85% GCV score = 50.493? Scale est. = 46.843??? n = 98 Assuming that you want to extract `3.079`. summary(pres.gam)$edf[1] #[1] 3.07938 A.K. I want to extract the components of a gam object. Sample code and data follows: library(MASS) library(mgcv)#package for GAM library(car)#to get the data data(Prestige) Prestige2<-na.omit(Prestige) pres.gam<-gam(prestige~s(income)+s(education),data =Prestige2) As an example I wish to extract the edf for income. In addition I want to learn how to systematically understand the components of structure pres.gam. I have tried str(pres.gam) which produce large output which is difficult to understand. Please explain using the edf component. Thank you