On Thu, 13 Apr 2006, Spencer Graves wrote:
Do you know of a reference that discusses alternative choices for
plotting positions for a normal probability plot? The documentation for
qqnorm says it calls ppoints, which returns qnorm((1:m-a)/(m+1-2*a))
with a = ifelse(n=10, 3/8, 1/2)?
On Fri, 14 Apr 2006, David Scott wrote:
On Thu, 13 Apr 2006, Spencer Graves wrote:
Do you know of a reference that discusses alternative choices for
plotting positions for a normal probability plot? The documentation for
qqnorm says it calls ppoints, which returns
Spencer:
I seem to remember that Jim Filliben did some work on this. Try checking the
references in this:
J. J. Filliben (1975)
The Probability Plot Correlation Coefficient Test for Normality
Technometrics, Vol. 17, No. 1, pp. 111-117
My experience agrees with yours: if sample sizes are