qint:

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

Usage

qint(x, q = 0.5, alpha = 0.05, pr = FALSE)

Arguments

x
q
alpha
pr

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, q = 0.5, alpha = 0.05, pr = FALSE) 
{
    if (pr) {
        if (sum(duplicated(x) > 0)) 
            print("Duplicate values detected; use hdpb")
    }
    n <- length(x)
    ii <- floor(q * n + 0.5)
    jj <- ii + 1
    if (ii <= 0) 
        stop("Cannot compute a confidence interval for this q")
    if (jj > n) 
        stop("Cannot compute a confidence interval for this q")
    jjm <- jj - 1
    iim <- ii - 1
    cicov <- pbinom(jjm, n, q) - pbinom(iim, n, q)
    while (cicov < 1 - alpha) {
        iim <- max(iim - 1, 0)
        jjm <- min(jjm + 1, n)
        if (iim == 0 && jjm == n) 
            break
        cicov <- pbinom(jjm, n, q) - pbinom(iim, n, q)
    }
    xsort <- sort(x)
    low <- xsort[iim + 1]
    hi <- xsort[jjm]
    if (cicov < 1 - alpha) {
        if (pr) 
            print("Warning: Desired probability coverage could not be achieved")
    }
    list(ci.low = low, ci.up = hi, ci.coverage = cicov)
  }

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