<div dir="ltr"><div class="gmail_default" style="font-family:tahoma,sans-serif">I'm sorry to make a mistake just now. The previous message sent didn't fullfill my meaning.</div><div class="gmail_default" style="font-family:tahoma,sans-serif">
<br></div><div class="gmail_default" style="font-family:tahoma,sans-serif"><span style="font-size:13px">I carefully inspected the code in the function </span><i style="font-size:13px"><b>resampledesign</b></i><span style="font-size:13px"> but I was quite confused by the codes in the bootstrap section (For paired design, the design matrix should be like this, design(1,:)=[1:N 1:N], </span><span style="font-size:13px">design(2,1:N)=1 and </span><span style="font-size:13px">design(2,N+1:2*N)=2 and N is for example the subject number</span><span style="font-size:13px">; and cfg.uvar=2</span><span style="font-size:13px">):</span></div>
<div class="gmail_default"><div class="gmail_default"><font face="tahoma, sans-serif">91 Nvar = size(design,1); % number of factors or regressors</font></div><div class="gmail_default"><font face="tahoma, sans-serif">92 Nrepl = size(design,2); % number of replications</font></div>
<div class="gmail_default"><font face="tahoma, sans-serif">...</font></div><div class="gmail_default"><font face="tahoma, sans-serif">...</font></div></div><div class="gmail_default"><div class="gmail_default"><font face="tahoma, sans-serif">248 units = design(cfg.uvar,:);</font></div>
<div class="gmail_default"><font face="tahoma, sans-serif">249 for k = 1:length(unique(units))</font></div><div class="gmail_default"><font face="tahoma, sans-serif">250 sel = find(units==k);</font></div><div class="gmail_default">
<font face="tahoma, sans-serif">251 indx(:,k) = sel;</font></div><div class="gmail_default"><font face="tahoma, sans-serif">252 Nrep(k) = length(sel);</font></div><div class="gmail_default"><font face="tahoma, sans-serif">253 end</font></div>
<div class="gmail_default"><font face="tahoma, sans-serif">254 resample = zeros(cfg.numrandomization, Nrepl);</font></div></div><div class="gmail_default"><font face="tahoma, sans-serif">...</font></div><div class="gmail_default">
<font face="tahoma, sans-serif">...</font></div><div class="gmail_default"><font face="tahoma, sans-serif"><div class="gmail_default">274 tmp = zeros(cfg.numrandomization*10, Nrepl/Nrep(1));</div><div class="gmail_default">
275 for i=1:cfg.numrandomization*10</div><div class="gmail_default">276 tmp(i,:) = <b>sort</b>(randsample(1:Nrepl/Nrep(1), Nrepl/Nrep(1)));</div><div class="gmail_default">277 end</div><div class="gmail_default">
<br></div><div class="gmail_default"><div class="gmail_default">278 tmp = unique(tmp, 'rows');</div><div class="gmail_default">279 fprintf('found %d unique rows in bootstrap matrix of %d bootstraps', size(tmp,1), cfg.numrandomization*10);</div>
</div><div class="gmail_default">...</div><div class="gmail_default">...</div><div class="gmail_default"><div class="gmail_default">292 for i=1:cfg.numrandomization</div><div class="gmail_default">293 for k=1:size(indx,1)</div>
<div class="gmail_default">294 resample(i,indx(k,:)) = indx(k,tmp(i,:));</div><div class="gmail_default">295 end</div><div class="gmail_default">296 end</div><div class="gmail_default"><br></div><div class="gmail_default" style>
My question was on the code in 276 line. These code was to generate a number of rand numbers (about cfg.numrandomization lines) in the range of 1 to Nrepl/Nrep(1), in which Nrepl is the number of replications in the design and Nrep is the number of repetition (Nrep(:)=2 for paired design). If the function '<b>sort</b>' is used, then every row of matrix tmp is the same, which will be 1,2,..., Nrepl/Nrep(1). And this will lead the 278 line to the result: temp=1:Nrepl/Nrep(1) (because of the function unique). This result is by no means what we want, I think. What we do want is several rows numbers with same range but with distinct orders. Only in this way, can we guarantee that each resample is not the same.</div>
<div class="gmail_default" style><br></div></div></font></div><div class="gmail_extra">
<br><br><div class="gmail_quote">On Tue, May 7, 2013 at 2:35 PM, Chao Wang <span dir="ltr"><<a href="mailto:chaowang0704@gmail.com" target="_blank">chaowang0704@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div dir="ltr">I<div> have been using field-trip. Recently, I tried to use it for statistic test by non-parametric method, e.g. bootstrap and permutation. As usual, the two method involve resample original data with or without replacement. I carefully inspected the code in the function <i><b>resampledesign</b></i> but I was quite confused by the method in the bootstrap section:</div>
<div><div><br></div></div><div><div><font face="tahoma, sans-serif">254resample = zeros(cfg.numrandomization, Nrepl);</font><br>
</div></div></div>
</blockquote></div><br></div></div>