.BG
.FN ppoints
.TL
Plotting Points for Q-Q Plots
.CS
ppoints(n,a)
.AG n
sample size for which plotting points desired (if `n' has
only 1 value) or data against which plot is to be made.
.AG a
Parameter that controls precise placement of plotting points,
`0<=a<=1'.
Default is `.5' if `n>10' or `.375' if `n<=10'.
.RT
the vector of probabilities, `p', such that `qdist(p)'
plotted against `sort(y)' gives a probability (Q-Q) plot of
`y' against the distribution of which `qdist' is the
quantile function.  Computes `p[i]=(i-a)/(n+1-2*a)'.
.SH REFERENCE
G. Blom,
.ul
Statistical Estimates and Transformed Beta Variables,
Wiley, New York, 1958.
.EX
plot(qlnorm(ppoints(y)),sort(y))   #log normal q-q plot
.KW distribution
.WR
