cv_lspath: Compute cross validation error

In sahirbhatnagar/eclustProject: High Dimensional Interactions with an Environment Variable

Description

functions used to calculate cross validation error and used by the cv.shim function

Usage

cv_lspath(outlist, x, y, foldid, nlambda, nlambda.beta, nlambda.gamma)

cvcompute(mat, foldid, nlams)

getmin_type(lambda, cvm, cvsd, type)

lambda.interp(lambda, s)

Arguments

outlist	list of cross validated fitted models. List is of length equal to nfolds argument in cv.shim function
x	Design matrix of dimension n x q, where n is the number of subjects and q is the total number of variables; each row is an observation vector. This must include all main effects and interactions as well, with column names corresponding to the names of the main effects (e.g. x1, x2, E) and their interactions (e.g. x1:E, x2:E). All columns should be scaled to have mean 0 and variance 1; this is done internally by the shim function.
y	response variable (matrix form) of dimension n x 1
foldid	numeric vector indicating which fold each observation belongs to
nlambda	total number of tuning parameter pairs. This includes those pairs of tuning parameters that didn't converge in the CV folds.
nlambda.beta	number of tuning paramters for the main effect
nlambda.gamma	number of tuning parameters for the interaction effects
type	should be one of "beta" or "gamma"
outlist	list containing results from cv.shim function. each element of the list is a run of shim_multiple_faster for each CV fold

Details

The output of the cv_lspath function only returns values for those tuning paramters that DID converge

Functions

• cvcompute: Computations for crossvalidation error

• getmin_type: Function that returns the tuning paramter corresponding to the minimum cross validated error and cross validated error within 1 standard error of the minimum

• lambda.interp: Interpolation function. Currently not implemented.

See Also

cv.shim

sahirbhatnagar/eclustProject documentation built on May 29, 2019, 12:58 p.m.