Fits multiple scam models of response~s(explanatory), choose the best scam for each explanatory variable and then produces a list of scam objects as well as a vector of deviance explained by each variable. One would likely want an E variables that explains more of the variance but you also need to consider the amount of data and the shape of the model fitted.
Presently, the function will fail on the inability to fit a scam model. It needs to be error proofed using tryCatch.
1 | best.E.f(x.matrix, y)
|
x.matrix |
a matrix of explanatory (E) variables |
y |
the response variable |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.