Dear Marco<br><br>I&#39;m assuming you are not counting subject as your first factor, and that you are modelling a repeated measures design. So if the first factor is group then you shouldn&#39;t use a  flexible factorial for this comparison. Tthis should be done instead with a two sample t-test in which you average the con images across your conditions (within subject) and then compare the two groups of averaged con images. If your first factor is not group then it is likely that the flexible factorial is more appropriate as it better models the intrasubject variance.<br>

<br><div dir="ltr"><div>Darren Gitelman, MD</div></div><br><br><div class="gmail_quote">On Wed, Sep 23, 2009 at 7:38 AM, Marco Sperduti <span dir="ltr">&lt;<a href="mailto:[log in to unmask]"><a href="/cgi-bin/wa-jisc.exe?LOGON=A3%3Dind0909%26L%3DSPM%26E%3Dquoted-printable%26P%3D4423283%26B%3D--0015174762483ad91804743eb012%26T%3Dtext%252Fhtml%3B%2520charset%3DISO-8859-1%26pending%3D" target="_parent" >[log in to unmask]</a></a>&gt;</span> wrote:<br>

<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td style="font-family: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; font-size: inherit; line-height: inherit; font-size-adjust: inherit; font-stretch: inherit;" valign="top">

Dear SPM users,<br><br>I have a 2x2 factorial design. I have modelled my second level analysis using a full factorial and a flexible factorial design. I have different results, for example with the full factorial the main effect of my first factor is not significant while with the flexible factorial it is.<br>

<br>Which analys can I trust more, and why?<br><br>Thank&#39;s a lot,<br><br>Marco<br></td></tr></tbody></table><br>



      </blockquote></div><br>