MATLAB: How to compare two time series of same length using sample entropy

comparing time-series

Hello! I am studying the behavior of two centroids (geometric centers) of two soccer teams during a small-sided game. I have already computed the centroids coordinates (x,y) across time and they are stored in my workspace as 'centroidA' (for team A) and 'centroidB' (for team B). Each of the aforementioned variables has several lines and two columns, the first being for the x- coordinates and the second column being for the y- coordinates. I want to verify how much coupled are the two centroids in the x- and y- directions using sample entropy!
I've found this code, but it can only take one time-series:
function [e,A,B]=Samplentropy(y,M,r)  
%function [e,A,B]=sampenc(y,M,r);
%



%Input
%
%y input data
%M maximum template length
%r matching tolerance
%
%Output
%
%e sample entropy estimates for m=0,1,...,M-1
%A number of matches for m=1,...,M
%B number of matches for m=1,...,M excluding last point
n=length(y);
lastrun=zeros(1,n);
run=zeros(1,n);
A=zeros(M,1);
B=zeros(M,1);
p=zeros(M,1);
e=zeros(M,1);
for i=1:(n-1)
   nj=n-i;
   y1=y(i);
   for jj=1:nj
      j=jj+i;      
      if abs(y(j)-y1)<r
         run(jj)=lastrun(jj)+1;
         M1=min(M,run(jj));
         for m=1:M1           
            A(m)=A(m)+1;
            if j<n
               B(m)=B(m)+1;
            end            
         end
      else
         run(jj)=0;
      end      
   end
   for j=1:nj
      lastrun(j)=run(j);
   end
end
N=n*(n-1)/2;
p(1)=A(1)/N;
e(1)=-log(p(1));
for m=2:M
   p(m)=A(m)/B(m-1);
   e(m)=-log(p(m));
end
Hope you can help!
Best wishes,
Pedro

Best Answer

If you want to compare the dependence of two time series using an information theoretic approach, a common thing to do is use mutual information. If you search the file exchange or the web, you'll find a number of MATLAB files to compute the mutual information.
Related Question