pmle: PMLE-penalized maximum likelihood estimate in linear...

In Shenshiny/StatComp21010: Three functions with homework answers

Description

A penalized maximum likelihood estimator using R

Usage

pmle(x, y, lam0 = NULL, LSE = FALSE)

Arguments

x	predictors, an n by p matrix with n > 1 and p > 1
y	response, an n-vector with n > 1
lam0	Initial penalty level. Default is sqrt(2 * log(p)/n)
LSE	If TRUE, compute least squares estimates after scaled Lasso selection. Default is FALSE

Value

sigma	the estimated noise level
coef	the estimated coefficients
fitted.value	the fitted value
residuals	the residuals
lse	the least square estimation after the seletion

Examples

## Not run: 
data(X)
attach(X)
data(Y)
attach(Y)
x = X
y = Y
pmle(x,y,lam0=3)$coef

## End(Not run)

Shenshiny/StatComp21010 documentation built on Dec. 23, 2021, 10:22 p.m.