select.ppmnet: Select a tuning parameter value from a 'ppmnet' object

In jeffdaniel/ppmnet: Regularized Spatial Point Process Models

Description

Selects a point from along the fitted regularization path of a 'ppmnet' object on the basis of a (composite) information criterion.

Usage

## S3 method for class 'ppmnet'
select(object, criterion = c("AIC", "BIC", "ERIC"), ...)

Arguments

object	A fitted ppmnet object.
criterion	The criterion by which to select the tuning parameter. One of "AIC", "BIC", or "ERIC".
...	Ignored

Value

A list containing lambda, the selected tuning parameter; coefs, the coefficients of the selected model; edf, the effective degrees of freedom for the regularization path; and criterion; the computed criterion values for the regularization path.

Examples

Qp <- quadscheme(Xp)
fitp <- ppmnet(Qp, exdata)
select(fitp, "BIC")

Qg <- quadscheme.logi(Xg)
fitg <- ppmnet(Qg, exdata, Geyer(5, 1), method = "logi", nlambda = 20)
select(fitg, "BIC")

jeffdaniel/ppmnet documentation built on Aug. 14, 2019, 6:31 a.m.