coef.cv.FuncompCGL: get coefficients or make coefficient predictions from a...

In Zhe-Research/compReg: Compositional Data Regression

Description

This function gets coefficients or makes coefficient predictions from a cross-validated FuncompCGL model, using the stored "FuncompCGL.fit" object, and the optimal value chosen for lam andk (degree of freedom of basis). Questionable!!!

Usage

## S3 method for class 'cv.FuncompCGL'
coef(object, trim = FALSE, s = c("lam.min",
  "lam.1se"), k = NULL, ...)

Arguments

object	fitted cv.FuncompCGL object.
trim	logical, used the trimmed result or not.
s	value(s) of the penalty parameter lam at which predictions are required. Default is the value s="lam.min" stored on the CV object, it is the value of lam for optimal k such that gives minimum mean cross-validated error. If s is numeric, it is taken as the value(s) of lam to be used.
k	value of df of basis at which predictions are required. Default is k = "k.min", it is the value of k that gives minimum mean cross-validated error. If k is a scaler, it is taken as the value of k to be used and it must be stored in cv.FuncompCGL object.
...	not used. Other arguments to predict.

Value

The coefficients at the requested values for lam and k.

Zhe-Research/compReg documentation built on May 28, 2019, 8:38 a.m.