基函数与平滑

R 中的广义可加模型（GAM）非线性建模

Noam Ross

Senior Research Scientist, EcoHealth Alliance

获得合适的拟合

$$\LARGE \text{拟合} = \text{似然} - \lambda \times \text{起伏度}$$

设定固定的平滑参数

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

通过受限最大似然进行平滑

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

设置基函数数量

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

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

使用默认值

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

R 中的广义可加模型（GAM）非线性建模