<div dir="ltr">Interpreting and averaging p-values is not the same thing. P-values answer a very specific question and are the last step of any inquiry, all averaging, separation, other combinations of data happen before a p-value is calculated.</div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">Am Mo., 12. Dez. 2022 um 11:35 Uhr schrieb Burcu Bayram via fieldtrip <<a href="mailto:fieldtrip@science.ru.nl">fieldtrip@science.ru.nl</a>>:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
Thank you very much for your reply!<br>
<br>
Would you be so kind to elaborate on why interpreting or averaging <br>
r-squared values or p-values does not make much sense? And why <br>
r-squared values give a very reasonable topography, but one that is so <br>
much different from the topography of beta values?<br>
<br>
Best regards,<br>
Burcu<br>
<br>
On 12.12.2022 08:18, Schoffelen, J.M. (Jan Mathijs) via fieldtrip wrote:<br>
> Hi Burcu,<br>
> <br>
> Conventially, the parameter estimates (i.e. the beta weights) are<br>
> taken to the second level for an inferential statistical test.<br>
> Averaging p-values, or r-squared values is usually not done, and also<br>
> does not make much sense.<br>
> <br>
> Best wishes,<br>
> Jan-Mathijs<br>
> <br>
> <br>
>> On 10 Dec 2022, at 17:07, Burcu Bayram via fieldtrip <br>
>> <<a href="mailto:fieldtrip@science.ru.nl" target="_blank">fieldtrip@science.ru.nl</a>> wrote:<br>
>> <br>
>> Dear FieldTrip community,<br>
>> <br>
>> I'm new to regression analysis of EEG data and unsure which regression <br>
>> outputs to use. Beta-coefficients give a very different pattern of <br>
>> results compared to r squared values or p-values, although all of them <br>
>> (to my understanding) should express a form of relation between the <br>
>> two datasets. We are looking for help regarding the interpretation of <br>
>> those data and which one to select for our analysis. In our model, <br>
>> behaviour is the predictor and EEG activity is the outcome. The <br>
>> datapoints for each are single experimental trials (~2000 per <br>
>> subject).<br>
>> So far, we just used simple linear regression, but the plan is to use <br>
>> multiple linear regression at a later stage.<br>
>> The idea is to plot and interpret the regression results as if they <br>
>> were EEG amplitudes. So we get a time course and a topography of <br>
>> regression results, that help us to determine where and when in the <br>
>> brain behavior predicts neural activity. Our main questions are:<br>
>> <br>
>> 1. Which value makes most sense to use as an indication of brain/ <br>
>> behavior relationship? The betas should provide the quality/ direction <br>
>> of the relationship, but don't say anything about how large or <br>
>> important that relationship is. The r squared or also the t or p <br>
>> values for each coefficient tell something about the strength of the <br>
>> relationship. The issue is, that they give really different activity <br>
>> patterns. You can see the topographies of beta values, r squared <br>
>> values and p-values in the attached images.<br>
>> <br>
>> 2. The second question is which of the single-subject regression <br>
>> outputs actually can be used for group level plots and statistics: Is <br>
>> it possible to average over e.g. betas or p-vales across subjects, and <br>
>> also do group level statistics with (e.g. compare group-level p-values <br>
>> or betas between two conditions)?<br>
>> <br>
>> Thank you so much in advance!<br>
>> <br>
>> Best regards,<br>
>> Burcu<br>
>> <beta_av_postmean.png><p_values_av_postmean.png><r_squared_av_postmean.png>_______________________________________________<br>
>> fieldtrip mailing list<br>
>> <a href="https://mailman.science.ru.nl/mailman/listinfo/fieldtrip" rel="noreferrer" target="_blank">https://mailman.science.ru.nl/mailman/listinfo/fieldtrip</a><br>
>> <a href="https://urldefense.com/v3/__https://doi.org/10.1371/journal.pcbi.1002202__;!!HJOPV4FYYWzcc1jazlU!-BVAi-vLCyuI-z25XshuL5Ot-zKj9ciiKIvw7cD8r0qhP2CQfYup6W8y10f8RVGleO0IZjn6YH1s39xwbLKu4dPeUFzFOfIwfYy5Qg$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://doi.org/10.1371/journal.pcbi.1002202__;!!HJOPV4FYYWzcc1jazlU!-BVAi-vLCyuI-z25XshuL5Ot-zKj9ciiKIvw7cD8r0qhP2CQfYup6W8y10f8RVGleO0IZjn6YH1s39xwbLKu4dPeUFzFOfIwfYy5Qg$</a><br>
> <br>
> <br>
> _______________________________________________<br>
> fieldtrip mailing list<br>
> <a href="https://mailman.science.ru.nl/mailman/listinfo/fieldtrip" rel="noreferrer" target="_blank">https://mailman.science.ru.nl/mailman/listinfo/fieldtrip</a><br>
> <a href="https://doi.org/10.1371/journal.pcbi.1002202" rel="noreferrer" target="_blank">https://doi.org/10.1371/journal.pcbi.1002202</a><br>
_______________________________________________<br>
fieldtrip mailing list<br>
<a href="https://mailman.science.ru.nl/mailman/listinfo/fieldtrip" rel="noreferrer" target="_blank">https://mailman.science.ru.nl/mailman/listinfo/fieldtrip</a><br>
<a href="https://doi.org/10.1371/journal.pcbi.1002202" rel="noreferrer" target="_blank">https://doi.org/10.1371/journal.pcbi.1002202</a><br>
</blockquote></div>