## Cross correlation negative lag time

### Sarah (view profile)

on 21 Sep 2012

Hi everybody, I am cross correlating two signals and plotting the lag times as delays in a histogram to see what the predominant delay is. I am getting a very prominant delag at lag time 0 to -1 hrs and am just wondering what this means in terms of which station is the causative one. By this I mean, which signal is seen first and whis is a result? Thank you for any help

## Products

No products are associated with this question.

### Wayne King (view profile)

on 21 Sep 2012
Edited by Wayne King

### Wayne King (view profile)

on 21 Sep 2012

If you look at the help for xcorr(), you'll see how the inputs are lagged with respect to each other. If the A input is delayed by 4 samples with respect to B and you use:

 [xc,lags] = xcorr(A,B,...)

You'll get the maximum at the positive lag 4.

However, if you enter

[xc,lags] = xcorr(B,A,...)


you'll get the maximum at negative lag 4.

For example:

    B = randn(40,1);
% A is a delayed version of B, delayed by 4 samples
A = [zeros(4,1) ; B];
[xc,lags] = xcorr(A,B,20);
stem(lags,xc)  % delay is positive
% now reverse order of inputs
[xc,lags] = xcorr(B,A,20);
figure;
stem(lags,xc) %delay is negative

In both cases, the delay is correctly indicated as 4.

Sarah

### Sarah (view profile)

on 21 Sep 2012

Thank you for that it clears things up quite a bit. So whatever parameter is first is the driving parameter, and is seen first if the two signals are plotted on top of one another?

Wayne King

### Wayne King (view profile)

on 21 Sep 2012

If you want a signal which is delayed in time relative to another to appear as a positive lag in the cross correlation, then enter that input first.

If you have a model where a signal Y is a delayed version of X, so that

Y(n) = X(n-\tau)


for some positive lag \tau, then if that is what you mean by X is driving Y, then entering

[xc,lags] = xcorr(Y,X);


gives you the maximum at lag \tau (the positive lag \tau)

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi test