Dear all,<div><br></div><div>I have a 3 X 3 factorial mixed design with one factor as stimulus type with three levels and another group factor with three levels. I am modelling this using the flexible factorial in spm5. Following the instructions from the Glascher and Gitelman tutorial, I modelled 3 factors - 1 -subject, 2- Group and 3 -Conditions along with main effects of group (Factor 2) and condition (Factor 3) and their interaction (2 and 3). </div>

<div> I have two questions concerning this-</div><div><br></div><div>1. The design matrix shows the betas for each regressor as gray (Although at no point in the pipeline does it show an error). Is that a potential problem for estimation?</div>

<div>2. What would be the best contrasts weights to estimate group and condition effects? Is it sufficient to use the T-contrast?</div><div><br></div><div>I would be grateful for any comments/answers.</div><div><br></div>

<div>Thanks!</div><div>Megha</div><div><div><br></div>-- <br>Megha Sharda<br>Graduate Student<br>National Brain Research Centre<br>Manesar, Gurgaon -122050<br>India<br>Ph: +919810943202<br>
</div>