[R] R: pp plot

Dr. Herwig Meschke HerwigMeschke at t-online.de
Thu Nov 24 14:35:57 CET 2005


To construct a nonparametric (1-alpha) confidence set for an arbitrary 
CDF F, you can use the Dvoretzky-Kiefer-Wolfowitz (DKW) inequality 
(e.g., see Wasserman, L. (2005). All of Statistics. 2nd, corr. printing. 
NY: Springer, p. 99).
With n=sample size and eps=sqrt(log(2/alpha)/(2*n)),
the lower and upper limits are pmax(F-eps ,0) and pmin(F+eps, 1).
Disadvantage: the sample size must be large.

Herwig

-- 
Dr. Herwig Meschke
Wissenschaftliche Beratung
Hagsbucher Weg 27
D-89150 Laichingen

phone +49 7333 210 417 / fax +49 7333 210 418
email HerwigMeschke at t-online.de
> hi all
> 
> i would like to know if anyone has a reference on how one would place
> the "bands" on the pp plot.
> 
> i want to test whether or not a certain data set comes from a particular
> distribution (not normal).
> 
> i've already plotted F(X(j)) vs j/(n+1)	where F(x) is the cum dist
> function, X(j) is the j'th order statistic and n is the sample size. 
> 
> a goole search gave arb references and thought some one one the list
> should definitely know how to solve this problem.
> 
> thanking you in advance
> allan




More information about the R-help mailing list