logLik: log likelihood function for fitted oem objects

In oem: Orthogonalizing EM: Penalized Regression for Big Tall Data

log likelihood function for fitted oem objects

Description

log likelihood function for fitted oem objects

log likelihood function for fitted cross validation oem objects

log likelihood function for fitted cross validation oem objects

Usage

## S3 method for class 'oem'
logLik(object, which.model = 1, ...)

## S3 method for class 'cv.oem'
logLik(object, which.model = 1, ...)

## S3 method for class 'xval.oem'
logLik(object, which.model = 1, ...)

Arguments

object	fitted "oem" model object.
which.model	If multiple penalties are fit and returned in the same oem object, the which.model argument is used to specify which model to plot. For example, if the oem object "oemobj" was fit with argument penalty = c("lasso", "grp.lasso"), then which.model = 2 provides a plot for the group lasso model.
...	not used

Examples

set.seed(123)
n.obs <- 2000
n.vars <- 50

true.beta <- c(runif(15, -0.25, 0.25), rep(0, n.vars - 15))
x <- matrix(rnorm(n.obs * n.vars), n.obs, n.vars)
y <- rnorm(n.obs, sd = 3) + x %*% true.beta

fit <- oem(x = x, y = y, penalty = c("lasso", "mcp"), compute.loss = TRUE)

logLik(fit)

logLik(fit, which.model = "mcp")


fit <- cv.oem(x = x, y = y, penalty = c("lasso", "mcp"), compute.loss = TRUE,
              nlambda = 25)

logLik(fit)

logLik(fit, which.model = "mcp")


fit <- xval.oem(x = x, y = y, penalty = c("lasso", "mcp"), compute.loss = TRUE, 
                nlambda = 25)

logLik(fit)

logLik(fit, which.model = "mcp")

oem documentation built on Oct. 13, 2022, 9:06 a.m.