Table 4: Gaussian location-scale additive model fitted to the semantic transparency ratings for derived words. te: tensor product smooth and s: thin plate regression spline.

A. parametric coefficients Estimate Std. Error t-value p-value

intercept [location] 5.5016 0.2564 21.4537 0.0001
intercept [scale] -0.4135 0.0401 -10.3060 0.0001

B. smooth terms edf Ref.df F-value p-value

te(activation diversity, word length) [location] 5.3879 6.2897 23.7798 0.0008
s(derivational lexome) [location] 14.3180 15.0000 380.6254 0.0001
s(activation diversity) [scale] 2.1282 2.5993 28.4336 0.0001
s(word length) [scale] 1.7722 2.1403 132.7311 0.0001