logLik.grpreg: logLik method for grpreg

In pbreheny/grpreg: Regularization Paths for Regression Models with Grouped Covariates

logLik method for grpreg

Description

Calculates the log likelihood and degrees of freedom for a fitted grpreg object.

Usage

## S3 method for class 'grpreg'
logLik(object, df.method = c("default", "active"), REML = FALSE, ...)

## S3 method for class 'grpsurv'
logLik(object, df.method = c("default", "active"), ...)

Arguments

object	A fitted grpreg or grpsurv object, as obtained from grpreg() or grpsurv()
df.method	How should effective model parameters be calculated? One of: "active", which counts the number of nonzero coefficients; or "default", which uses the calculated df returned by grpreg. Default is "default".
REML	Use restricted MLE for estimation of the scale parameter in a gaussian model? Default is FALSE.
...	For S3 method compatibility.

Details

Exists mainly for use with 'AIC' and 'BIC'.

Value

Returns an object of class 'logLik', in this case consisting of a number (or vector of numbers) with two attributes: 'df' (the estimated degrees of freedom in the model) and 'nobs' (number of observations).

The 'print' method for 'logLik' objects is not intended to handle vectors; consequently, the value of the function does not necessarily display correctly. However, it works with 'AIC' and 'BIC' without any glitches and returns the expected vectorized output.

Author(s)

Patrick Breheny

See Also

grpreg

Examples

data(Birthwt)
X <- Birthwt$X
y <- Birthwt$bwt
group <- Birthwt$group
fit <- grpreg(X,y,group,penalty="cMCP")
logLik(fit) ## Display is glitchy for vectors
AIC(fit)
BIC(fit)

pbreheny/grpreg documentation built on April 3, 2024, 3:53 p.m.