gets percentiles for TD rank curve
tdrankperc( td, percentiles = c( 0.5, 1, 2, 5, 95 ),
type = c( "quantile", "(i-1)/(n-1)", "i/(n+1)", "i/n" ),
smooth = TRUE, smoothFunction = tdrankglm )table with total-deviation values
percentiles at which to calculate cutoff values
see wtd.quantile for a list of different options
whether to use a function to smooth the results or not. Default is TRUE
if smooth is TRUE is true, the function to use for smoothing. Default is tdrankglm, a GLM fit which was proven to do a good fit for average over subject of TD rank curves. This function is not really a smoothing procedure, but a parametric fit
percentiles for TD rank curves
details