Mercurial > hg > ltpda
comparison m-toolbox/classes/+utils/@math/Kurt.m @ 0:f0afece42f48
Import.
author | Daniele Nicolodi <nicolodi@science.unitn.it> |
---|---|
date | Wed, 23 Nov 2011 19:22:13 +0100 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:f0afece42f48 |
---|---|
1 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% | |
2 % | |
3 % Compute the sample (bias-corrected) excess kurtosis. | |
4 % | |
5 % CALL | |
6 % | |
7 % p = Kurt(x); | |
8 % | |
9 % VERSION: $Id: Kurt.m,v 1.1 2011/02/25 10:04:07 congedo Exp $ | |
10 % | |
11 % HISTORY: 25-02-2011 G. Congedo | |
12 % | |
13 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% | |
14 | |
15 function k = Kurt(x) | |
16 | |
17 n = numel(x); | |
18 mu4 = sum((x-mean(x)).^4)/n; | |
19 sig = sqrt(sum((x-mean(x)).^2)/n); | |
20 k = mu4/(sig)^4; | |
21 | |
22 % Bias correction | |
23 k = (n-1)/(n-2)/(n-3)*((n+1)*k-3*(n-1)); | |
24 | |
25 end |