[FieldTrip] ITC and harmonic artefacts?

[Schoffelen, J.M. (Jan Mathijs)]

Hi Ivo,

I understand less than half of what you are writing. If you don’t provide any additional details about what (and how) you are trying to achieve, the only thing we can do as readership of this list (about 1800 people), is to call in the cavalry.

I asked my pal chatGPT, and this is what I got for an answer:



"It sounds like you are observing an effect in your inter-trial coherence analysis that is influenced by the distance between the time-points defining the trial-start.

One possibility is that you are observing harmonics of the frequencies of interest, as you suggested. Harmonics are multiples of a given frequency, and they can produce similar patterns of activity in the brain. Therefore, it's possible that your analysis is picking up on harmonics of the frequencies you're interested in.

Another possibility is that there may be some kind of artifact in your data that is causing the effect. For example, if there is some kind of noise or artifact in the data that is strongest at particular time intervals, this could cause the coherence values to be higher or lower at those intervals.

To help determine the cause of the effect you're observing, you could try a few things:

  *
Check your data for artifacts: Look at the raw data to see if there are any obvious sources of noise or artifact that could be causing the effect you're observing. You could also try preprocessing the data differently (e.g., applying different filters, using different reference electrodes) to see if this changes the results.
  *
Conduct a control analysis: Run a control analysis where you randomly shuffle the trial-start times and then compute the coherence values. This will help determine if the effect you're observing is due to the specific trial-start times you've chosen or if it is a more general effect.
  *
Consider other possible explanations: Think about other possible explanations for the effect you're observing. For example, it could be related to the way the brain is processing the stimuli you're presenting, or it could be related to some other aspect of the experimental design.

Overall, it's difficult to say exactly what is causing the effect without more information, but these are some things you could try to help narrow down the possibilities."



Perhaps that will help to get you going.

Good luck,
Jan-Mathijs



On 8 May 2023, at 13:04, Ivaylo Iotchev via fieldtrip <fieldtrip at science.ru.nl<mailto:fieldtrip at science.ru.nl>> wrote:

Dear community,

for some reason choosing the distancing between time-points defining trial-start for my inter-trial coherence analysis seems to affect the results... high coherence is observed for each frequency which is x/distance. What is funny is that trial duration and exact timing of pre-stimulus baseline and post-stimulus end are not influencing this picture, only the distance between the points that define trial start. For example if I space my trials starting points 750 milliseconds apart, I will get increases for 1.3 Hz, 2.6 Hz, 4 Hz... eventually 8 Hz... and so on...

To some extent I wouldn't be surprised if these are effects related to harmonics and I frankly do not expect a zero value for frequencies that are harmonic to the frequencies of interest, but maybe I am running up an artefact??

Bests,

Ivo
_______________________________________________
fieldtrip mailing list
https://mailman.science.ru.nl/mailman/listinfo/fieldtrip
https://urldefense.com/v3/__https://doi.org/10.1371/journal.pcbi.1002202__;!!HJOPV4FYYWzcc1jazlU!4SCrZ_DqN1nri9GmVju9DYmBzMHuZQY-8-u-6WziIXAseaG7LxEk2GKR3CmdM2aT2OHklcPd8qRPNc7R1KpoxDQ5v8tGddzvKu7XWQ$

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20230510/1393f1b3/attachment.htm>