n <- 100
p <- 20
x=matrix(rnorm(n*p),n,p)
y=rnorm(n)
fit1=glmnet(x = x, y = y,
weights = rep(1, times = n), penalty.factor = rep(1, times = p),
alpha = 1,
nlambda = 100, lambda.min.ratio = 0.001,
standardize = FALSE,
intercept = FALSE,
thresh = 1e-8,
type.gaussian = "naive")
w <- rep(1, times = n)
v <- w / sum(w)
v <- sqrt(v)
y <- Comp_data$y
y1 <- v * y
ys <- as.numeric(sqrt(crossprod(y1) - crossprod(v, y1)^2))
y1 <- y1 / ys
crossprod(y1 - mean(y1))
comp <- classo(y = drop(y1 * sqrt(n)), Z = x, Zc = NULL, intercept = FALSE,
pf = rep(1, times = p),
lam = fit1$lambda,
nlam = 100, lambda.factor = 0.001,
dfmax = p,
mu_ratio = 0, tol = 0,
outer_maxiter = 1e8, outer_eps = 1e-10, inner_maxiter = 1e8, inner_eps = 1e-10)
comp$beta[, 50]
fit1$beta[, 50]
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.