<div dir="ltr">Dear Nils,<div><br></div><div>> Can anyone confirm Makoto's and my assumption?<br></div><div><br></div><div><span style="font-size:12.8px">> Actually, when you use pop_newtimef with FDR it outputs something like "ERSP correction for multiple comparisons using FDR, alpha_fdr = 0.024876" which I I find a little misleading. Because the number printed is actually the return value of the fdr function, namely the p-value threshold.</span><br></div><div><span style="font-size:12.8px"><br></span></div><div><span style="font-size:12.8px">See the highlighted parts below.</span></div><div><br></div><div>This is from newtimef() line 1439</div><div><br></div><div><div>if strcmpi(g.mcorrect, 'fdr')</div><div><span style="background-color:rgb(234,153,153)"> alphafdr = fdr(exactp_ersp, g.alpha);</span></div></div><div><br></div><div>This is from 'help fdr'</div><div><br></div><div><div>>> help fdr</div><div> fdr() - compute false detection rate mask</div><div> </div><div> Usage:</div><div> >> [p_fdr, p_masked] = fdr( pvals, alpha);</div><div> </div><div> Inputs:</div><div> pvals - vector or array of p-values</div><div> alpha - threshold value (non-corrected). If no alpha is given</div><div> each p-value is used as its own alpha and fdr corrected</div><div> array is returned.</div><div> fdrtype - ['parametric'|'nonParametric'] fdr type. Default is </div><div> 'parametric'.</div><div> </div><div> Outputs:</div><div><span style="background-color:rgb(234,153,153)"> p_fdr - pvalue used for threshold (based on independence</span></div><div><span style="background-color:rgb(234,153,153)"> or positive dependence of measurements)</span></div><div> p_masked - p-value thresholded. Same size as pvals.</div><div> </div><div> Author: Arnaud Delorme, SCCN, 2008-</div><div> Based on a function by Tom Nichols</div><div> </div><div> Reference: Bejamini & Yekutieli (2001) The Annals of Statistics</div></div><div><br></div><div><br></div><div>So you are right, alphafdr should be the 'pvalue used for threshold'</div><div><br></div><div>Makoto</div><div><br></div><div><br></div><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Jan 27, 2017 at 12:52 AM, Nils Hachmeister <span dir="ltr"><<a href="mailto:nils.hachmeister@uni-bielefeld.de" target="_blank">nils.hachmeister@uni-bielefeld.de</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<div bgcolor="#FFFFFF">
<p>Hello,</p>
<p>thanks for your reply. I agree: The only way I could imagine how
to pass an alpha value from the GUI to the function is by putting
it in the only remaining field which is related to that topic.
That would be the field where I would put my p-value threshold
when I were using FDR (or some other means of multiple comparison
correction). Hence, my, and apparently also your assumption is
that the field for p-value threshold is somewhat double use: It
changes its meaning (albeit not its label) when you are doing FDR,
now taking the FDR alpha value. However, because the alpha
parameter of the fdr-function is optional it would also be
possible that you cannot put the alpha value at all, using the
GUI. However, then the results should not change depending on the
value I put into the p-value threshold field, as FDR determines
its own p-value threshold and the value I put into the p-value
threshold field should be ignored. But the results clearly depend
on the value I put into that field, which is, in my opinion, a
strong indication that our assumption is, indeed, true.<br>
</p>
<p>Can anyone confirm Makoto's and my assumption?</p>
<p>Thanks</p><span class="gmail-HOEnZb"><font color="#888888">
<p>Nils<br>
</p></font></span><div><div class="gmail-h5">
<div class="gmail-m_-9217407835490145585moz-cite-prefix">Am 26.01.2017 um 23:00 schrieb Makoto
Miyakoshi:<br>
</div>
</div></div><blockquote type="cite"><div><div class="gmail-h5">
<div dir="ltr">Dear Nils,
<div><br>
</div>
<div>I pasted the results from 'help fdr'. Apparently, it takes
only two inputs, p-values and alpha. So if you use any value
other than p-values, that should be alpha.</div>
<div><br>
</div>
<div>Makoto</div>
<div><br>
</div>
<div>%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%<wbr>%%%%%</div>
<div>
<div>>> help fdr</div>
<div> fdr() - compute false detection rate mask</div>
<div> </div>
<div> Usage:</div>
<div> >> [p_fdr, p_masked] = fdr( pvals, alpha);</div>
<div> </div>
<div> Inputs:</div>
<div> pvals - vector or array of p-values</div>
<div> alpha - threshold value (non-corrected). If no
alpha is given</div>
<div> each p-value is used as its own alpha and
fdr corrected</div>
<div> array is returned.</div>
<div> fdrtype - ['parametric'|'nonParametric'] fdr type.
Default is </div>
<div> 'parametric'.</div>
<div> </div>
<div> Outputs:</div>
<div> p_fdr - pvalue used for threshold (based on
independence</div>
<div> or positive dependence of measurements)</div>
<div> p_masked - p-value thresholded. Same size as pvals.</div>
<div> </div>
<div> Author: Arnaud Delorme, SCCN, 2008-</div>
<div> Based on a function by Tom Nichols</div>
<div> </div>
<div> Reference: Bejamini & Yekutieli (2001) The Annals
of Statistics</div>
</div>
<div>%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%<wbr>%%%%%</div>
</div>
</div></div><div class="gmail_extra"><br>
<div class="gmail_quote"><div><div class="gmail-h5">On Wed, Jan 25, 2017 at 12:55 AM, Nils
Hachmeister <span dir="ltr"><<a href="mailto:nils.hachmeister@uni-bielefeld.de" target="_blank">nils.hachmeister@uni-<wbr>bielefeld.de</a>></span>
wrote:<br>
</div></div><div><div class="gmail-h5"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">Hi
everyone,<br>
<br>
I'm using the study structure and aim to generate different
plots including statistical testing (non-parametric) with
multiple comparison correction, namely FDR. I used FDR
before (in a context unrelated to eeglab) and it is my
understanding that you pass a parameter alpha to it. FDR
returns a (common) threshold for p-values which guarantees
that the expected rate of type-I errors among all rejections
of the 0-hypothesis is smaller or equal to alpha.<br>
<br>
Now, in the statistics menu in the eeglab gui and the
documentation at <a href="https://sccn.ucsd.edu/wiki/Chapter_06:_Study_Statistics_and_Visualization_Options" rel="noreferrer" target="_blank">https://sccn.ucsd.edu/wiki/Cha<wbr>pter_06:_Study_Statistics_and_<wbr>Visualization_Options</a>
I cannot really find that notion. There is no mention of a
parameter nor any constraints regarding the rate of type-I
errors. However, I noticed that when passing a value to the
edit-field labeled threshold the results change pretty much
in a way consistent with that field being used as FDR-alpha.
But from the documentation I cannot confirm this assumption.
Can anybody here confirm this?<br>
<br>
Best<br>
<br>
Nils<br>
<br>
______________________________<wbr>_________________<br>
Eeglablist page: <a href="http://sccn.ucsd.edu/eeglab/eeglabmail.html" rel="noreferrer" target="_blank">http://sccn.ucsd.edu/eeglab/ee<wbr>glabmail.html</a><br>
To unsubscribe, send an empty email to <a href="mailto:eeglablist-unsubscribe@sccn.ucsd.edu" target="_blank"></a><a class="gmail-m_-9217407835490145585moz-txt-link-abbreviated" href="mailto:eeglablist-unsubscribe@sccn.uc" target="_blank">eeglablist-unsubscribe@sccn.uc</a><wbr><a href="http://sd.edu">sd.edu</a><br>
For digest mode, send an email with the subject "set digest
mime" to <a href="mailto:eeglablist-request@sccn.ucsd.edu" target="_blank">eeglablist-request@sccn.ucsd.e<wbr>du</a><br>
</blockquote>
</div></div></div>
<br>
<br clear="all">
<div><br>
</div><span class="gmail-">
-- <br>
<div class="gmail-m_-9217407835490145585gmail_signature">
<div dir="ltr">Makoto Miyakoshi<br>
Swartz Center for Computational Neuroscience<br>
Institute for Neural Computation, University of California
San Diego<br>
</div>
</div>
</span></div>
</blockquote>
<br>
</div>
</blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr">Makoto Miyakoshi<br>Swartz Center for Computational Neuroscience<br>Institute for Neural Computation, University of California San Diego<br></div></div>
</div></div>