基底函式與平滑化

R 中的廣義加法模型（GAM）之非線性建模

Noam Ross

Senior Research Scientist, EcoHealth Alliance

取得合適的擬合

$$\LARGE \text{擬合} = \text{概似} - \lambda \times \text{擺動度}$$

設定固定的平滑參數

gam(y ~ s(x), data = dat, sp = 0.1)
gam(y ~ s(x, sp = 0.1), data = dat)

以受限最大概似進行平滑

gam(y ~ s(x), data = dat, method = "REML")

設定基底函式數量

gam(y ~ s(x, k = 3), data = dat, method = "REML")

gam(y ~ s(x, k = 10), data = dat, method = "REML")

使用預設值

gam(y ~ s(x), data = dat, method = "REML")

R 中的廣義加法模型（GAM）之非線性建模