[Eeglablist] pop_est_validateMVAR

Tyler Grummett tyler.grummett at flinders.edu.au
Sun Mar 2 20:21:22 PST 2014


Hello all,

Recently Ive been trying to learn the SIFT toolbox and everything has been running relatively smoothly until I have tried to validate my MVAR measures and it gives me the following error.

>> [ whitestats, PC, stability] = pop_est_validateMVAR(ALLEEG,0,'whitenessCriteria', {'Ljung-Box','ACF','Box-Pierce','Li-McLeod'})
checking condition ...
Using 50 lags for covariance estimation.
checking condition ...
Using 50 lags for covariance estimation.
Index exceeds matrix dimensions.

Error in est_checkMVARWhiteness (line 132)
        residuals =
        est_mvarResiduals(squeeze(EEG.CAT.srcdata(:,g.winStartIdx(t):g.winStartIdx(t)+winLenPnts-1,:)),
        ...

Error in pop_est_validateMVAR (line 232)
        whitestats = est_checkMVARWhiteness(ALLEEG(cond),MODEL(cond),typeproc,g);


>From having a rough look at it, it would appear that the part of the code that does:

g.winStartIdx(t):g.winStartIdx(t)+winLenPnts-1?

generates a number greater than the number of columns in EEG.CAT.srcdata

I dont really understand what is going on.

Tyler



*************************

Tyler Grummett ( BBSc, BSc(Hons I))
PhD Candidate
Brain Signals Laboratory
Flinders University
Rm 5A301
Ext 66124
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20140303/7f1ba65f/attachment.html>


More information about the eeglablist mailing list