view m-toolbox/classes/+utils/@math/SKcriticalvalues.m @ 23:a71a40911c27
database-connection-manager
Update check for repository connection parameter in constructors
author |
Daniele Nicolodi <nicolodi@science.unitn.it> |
date |
Mon, 05 Dec 2011 16:20:06 +0100 (2011-12-05) |
parents |
f0afece42f48 |
children |
|
line source
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%
% Compute critical values of the Smirnov - Kolmogorov distribution
%
% CALL
%
% [F,X] = SKcriticalvalues(Y);
%
%
% INPUT
%
% - Y, a data series
%
% References:
% [1] Leslie H. Miller, Table of Percentage Points of Kolmogorov
% Statistics, Journal of the American Statistical Association,
% Vol. 51, No. 273 (Mar., 1956), pp. 111-121
%
%
% L Ferraioli 06-12-2010
%
% $Id: SKcriticalvalues.m,v 1.4 2011/03/31 15:38:18 luigi Exp $
%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function cVal = SKcriticalvalues(n1,n2,alph)
if isempty(n2)
n = n1; % test against theoretical distribution
else
n = n1*n2/(n1+n2); % test of two empirical distributions
end
A = 0.09037*(-log10(alph)).^1.5 + 0.01515*log10(alph).^2 - 0.08467*alph - 0.11143;
asympt = sqrt(-0.5*log(alph)./n); % Smirnov asymptothic formula
cVal = asympt - 0.16693./n - A./n.^1.5;
end