cell.glh: Confidence ellipse for estimated parameters in Wald test

In gmonette/spida: Collection of miscellaneous functions for mixed models etc. prepared for SPIDA 2009+ (development version)

Usage

cell.glh(obj, which.coef = 1:2, levels = 0.95, Scheffe = FALSE, dfn = 2, center.pch = 19, center.cex = 1.5, segments = 51, xlab, ylab, las = par("las"), col = palette()[2], lwd = 2, lty = 1, add = FALSE, ...)

Arguments

obj
which.coef
levels
Scheffe
dfn
center.pch
center.cex
segments
xlab
ylab
las
col
lwd
lty
add
...

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 (obj, which.coef = 1:2, levels = 0.95, Scheffe = FALSE, 
    dfn = 2, center.pch = 19, center.cex = 1.5, segments = 51, 
    xlab, ylab, las = par("las"), col = palette()[2], lwd = 2, 
    lty = 1, add = FALSE, ...) 
{
    obj <- obj[[1]]
    coef <- obj$coef[which.coef]
    xlab <- if (missing(xlab)) 
        paste(names(coef)[1], "coefficient")
    ylab <- if (missing(ylab)) 
        paste(names(coef)[2], "coefficient")
    dfd <- obj$anova$denDF
    shape <- obj$vcov[which.coef, which.coef]
    ret <- ell(coef, shape, sqrt(dfn * qf(levels, dfn, dfd)))
    colnames(ret) <- c(xlab, ylab)
    ret
  }

gmonette/spida documentation built on May 17, 2019, 7:25 a.m.