.BG
.FN lars
.TL
Fits Least Angle Regression, Lasso and Infinitesimal Forward Stagewise regression models
.DN
These are all variants of Lasso, and provide the entire sequence of
coefficients and fits, starting from zero, to the least squares fit.
.CS
lars(x, y, type=c("lasso", "lar", "forward.stagewise"))
.RA
.AG x
matrix of predictors
.AG y
response 
.AG type
One of  "lasso", "lar"  or "forward.stagewise". The names can be abbreviated to any unique
substring. Default is "lasso".
.AG trace
If TRUE, lars prints out its progress
.OA
.AG Gram
The X'X matrix; useful for repeated runs (bootstrap) where a large X'X
stays the same.
.AG eps
An effective zero
.AG max.steps
Can limit the number of steps taken; the default is to go all the way.
.AG use.Gram
When the number m of variables is very large, i.e. larger than N, then
you may not want LARS to precompute the Gram matrix. Default is use.Gram=T
.RT
A "lars" object is returned, for which print, plot and predict
methods exist.
.DT
LARS is described in detail in Efron, Hastie, Johnstone and Tibshirani
(2002). With the "lasso" option, it computes the complete lasso
solution simultaneously for ALL values of the shrinkage parameter in
the same computational cost as a least squares fit.
.SH REFERENCES
Efron, Hastie, Johnstone and Tibshirani (2003), "Least Angle
Regression", Annals of Statistics (with discussion).
Hastie, Tibshirani and Friedman (2002) Elements of Statistical
Learning, Springer, NY.
.SA
print, plot, and predict methods for lars
.EX
object <- lars(x,y,type=lasso)
plot(object)
.KW Lasso, Forward Stagewise
.WR