Outlier detection and robust regression with a ridge type penalty on the outlier indicator gamma. Allow non sparse outliers and require known noise standard deviation.
Usage
ridge(X, Y, H, sigma)
Arguments
X
an N by k design matrix
Y
an N by 1 response vector
H
an N by N projection matrix X(X'X)^{-1}X'
sigma
a numeric, noise standard deviation
Value
p
an N by 1 vector of p-values for each of the N genes
gamma
an N by 1 vector of estimated primary variable gamma