conc2:

In musto101/wilcox_R: What the package does (short line)

Usage

conc2(x, y, start = l1fit(x, y)$coef)

Arguments

x
y
start

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (x, y, start = l1fit(x, y)$coef) 
{
    nc <- dim(x)[2] + 1
    res <- y - (x %*% start[2:nc] + start[1])
    ares <- abs(res)
    cov <- ceiling(length(y)/2)
    m <- sort(ares, partial = cov)[cov]
    old <- sum(ares[ares <= m])
    new <- old - 1
    ct <- 0
    while (new < old) {
        ct <- ct + 1
        start <- l1fit(x[ares <= m, ], y[ares <= m])$coef
        res <- y - (x %*% start[2:nc] + start[1])
        ares <- abs(res)
        m <- sort(ares, partial = cov)[cov]
        new <- sum(ares[ares <= m])
        if (new < old) {
            old <- new
            new <- new - 1
        }
    }
    list(coef = start, ct = ct)
  }

musto101/wilcox_R documentation built on May 23, 2019, 10:52 a.m.