This internal function, called by fosr()
when method="OLS"
,
performs efficient leave-one-function-out cross-validation using
Demmler-Reinsch orthogonalization to choose the smoothing parameter.
lofocv(Y, X, S1, argvals, lamvec = NULL, constr = NULL, maxlam = NULL)
if lamvec=NULL
, a list (returned by optimize
) with
elements minimum
and objective
giving, respectively, the
chosen smoothing parameter and the associated cross-validation score.
Otherwise a 2-column table with the candidate smoothing parameters in the
first column and the corresponding cross-validation scores in the second.
matrix of responses, e.g. with columns corresponding to basis function coefficients.
model matrix.
penalty matrix.
values where the functions are evaluated
vector of candidate smoothing parameter values. If
NULL
, smoothing parameter is chosen by optimize
.
matrix of linear constraints.
maximum smoothing parameter value to consider (when
lamvec=NULL
).
Philip Reiss phil.reiss@nyumc.org and Lei Huang
fosr
, pwcv