cv.cdlm: Cross validation for penalized linear model for compound...

In sdzhao/cole: COmpound Loss Emporium

Cross validation for penalized linear model for compound decision problems

Description

Chooses tuning parameter M in the penalized version of cdlm, using cross validation.

Usage

cv.cdlm(
  Y,
  s2,
  C,
  CY,
  CN = NULL,
  N = NULL,
  Lp = 1,
  nfolds = 2,
  M.min = 0,
  M.max = 5,
  nM = 11,
  verbose = FALSE
)

Arguments

Y	observed data (n x 1)
s2	unbiased estimate of variance of Y (n x 1)
C	main effects in the linear regression (n x p_C)
CY	terms in the linear regression that interact with Y (n x p_Y)
CN	terms in the linear regression that interact with Y_i_k for i_k in the ith row of N. This should be a list of length q, where the kth item in the list is an n x p_k matrix.
N	neighbors of each index (n x q). This encodes structural information, where the ith row of N contains indices that are expected to be similar to the ith parameter of interest.
Lp	p norm
nfolds	number of folds of CV
M.min	minimum value of M to consider
M.max	largest value of M to consider
nM	number of M to fit, equally spaced between M.min and M.max inclusive
verbose	if TRUE, prints a message every time a fold is fit

Value

Ms	list of M values that were tried
M.opt	optimal M value
b	estimated regression coefficients
est	estimated parameters of interest

Examples

n = 10
set.seed(1)
theta = sort(rnorm(n))
s2 = abs(theta) + runif(n)
Y = theta + rnorm(n, sd = sqrt(s2))
C = cbind(1, s2)
CY = cbind(1, 1 / s2)
N = cbind(c(n, 1:(n - 1)), c(2:n, 1))
CN = rep(list(matrix(1, n, 1)), ncol(N))

fit = cv.cdlm(Y, s2, C, CY, CN, N, Lp = 1, nfolds = 5)
mean((theta - fit$est)^2)

sdzhao/cole documentation built on May 2, 2022, 9:42 a.m.