最近,当我研究lm.ridge
函数时,我发现这个函数有完全不同的系数,我不知道哪个是正确的,而不是与情节比较。
例如,
longley #lm.ridge example
names(longley)[1] <- "y"
rid.long <- lm.ridge(y ~ ., longley) #set lambda = 0 as OLS
list(rid.long) #it is the same as coef(rid.long)
[[1]]
GNP Unemployed Armed.Forces Population Year Employed
2946.85636017 0.26352725 0.03648291 0.01116105 -1.73702984 -1.41879853 0.23128785
coef(rid.long) #it is the same as list(rid.long)
GNP Unemployed Armed.Forces Population Year Employed
2946.85636017 0.26352725 0.03648291 0.01116105 -1.73702984 -1.41879853 0.23128785
rid.long$coef #it is totally different above two, and same as plot
GNP Unemployed Armed.Forces Population Year Employed
25.3615288 3.3009416 0.7520553 -11.6992718 -6.5403380 0.7864825
plot(lm.ridge(y ~ ., longley, lambda = seq(0,0.1,0.001)))
为什么示例图中的y轴捕获rid.long$coef
作为默认值,但不是coef(rid.long)
?这两个载体之间有什么不同?当我绘制脊线迹线时,我怎么能(或应该)改变y轴分量?我还查看了帮助附件中的coef
方法解释,但我仍然无法区分它们。