Cellwise regularized robust sparse regression (with a specific lambda)

Usage

sregcell_lambda(
  y,
  x,
  softbeta = TRUE,
  softdelta = TRUE,
  softzeta = TRUE,
  lambda_delta = 2.56,
  lambda_zeta = 2.56,
  lambda = 0,
  alpha = 0.5,
  tol = 0.001,
  maxiter = 100
)

Arguments

y: n-dimensional response vector
x: nxp design matrix
softbeta: whether to use soft/hard threshold for beta
softdelta: whether to use soft/hard threshold for delta (outliers in x)
softzeta: whether to use soft/hard threshold for zeta (outliers in y)
lambda_delta: tuning parameter of delta
lambda_zeta: tuning parameter of zeta
lambda: tuning parameter of beta
alpha: the importance factor of the regression loss (between 0-1, by default is 0.5)
tol: the tolerance of convergence, by default is 1e-3
maxiter: number of iterations, by default is 100

Value

intercept: the estimated intercept

betahat: the estimated vector of regression coefficients

deltahat: the estimated outlying parts in the design matrix

zetahat: the estimated outlying parts in the response

...

Examples



data = genevar()
y = data$y
x = data$x
fit = sregcell_lambda(y,x, lambda = 1)