 |
 |
I would only recommend that option for non-repeated measures. If you were to make the interaction at the first-level and then bring that contrast to the second-level, then you could use a one-sample t-test and then de-weight the outliers. Best Regards, Donald McLaren ================= D.G. McLaren, Ph.D. Research Fellow, Department of Neurology, Massachusetts General Hospital and Harvard Medical School Postdoctoral Research Fellow, GRECC, Bedford VA Website: http://www.martinos.org/~mclaren Office: (773) 406-2464 ===================== This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is intended only for the use of the individual or entity named above. If the reader of the e-mail is not the intended recipient or the employee or agent responsible for delivering it to the intended recipient, you are hereby notified that you are in possession of confidential and privileged information. Any unauthorized use, disclosure, copying or the taking of any action in reliance on the contents of this information is strictly prohibited and may be unlawful. If you have received this e-mail unintentionally, please immediately notify the sender via telephone at (773) 406-2464 or email. On Fri, Jun 7, 2013 at 11:40 AM, anli <[log in to unmask]> wrote: > Hi Donald > > Many thanks for your commends. I corrected the interaction contrast now. > Just a one more question, would you recommend to turn on the "automatic > outlier de-weighting" option when running Higher-level analysis? > > Best wishes, > > Anli > > > On Jun 7, 2013, at 11:37 AM, MCLAREN, Donald wrote: > > Your design matrix is correct, but your interaction contrast should be 0 0 > 1 0.... > > The contrast you have for the interaction is testing the the effect of > factor1 is different form the effect of factor2. The interaction tests the > effect of factor1 is different for the levels of factor2. > > Forming a contrast: > (1) Determine the null hypothesis. [e.g. interaction=0] > (2) Make the equation equal to 0. [In this case it already equals 0.] > (3) Use the coefficients of each term as the contrast weight. [In this > case the only column with a weight is the interaction column. The weight is > 1. All other columns are 0.] > > > Best Regards, Donald McLaren > ================= > D.G. McLaren, Ph.D. > Research Fellow, Department of Neurology, Massachusetts General Hospital > and > Harvard Medical School > Postdoctoral Research Fellow, GRECC, Bedford VA > Website: http://www.martinos.org/~mclaren > Office: (773) 406-2464 > ===================== > This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED > HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is > intended only for the use of the individual or entity named above. If the > reader of the e-mail is not the intended recipient or the employee or agent > responsible for delivering it to the intended recipient, you are hereby > notified that you are in possession of confidential and privileged > information. Any unauthorized use, disclosure, copying or the taking of any > action in reliance on the contents of this information is strictly > prohibited and may be unlawful. If you have received this e-mail > unintentionally, please immediately notify the sender via telephone at > (773) > 406-2464 or email. > > > On Thu, Jun 6, 2013 at 11:53 PM, WG <[log in to unmask]> wrote: > >> Hi All >> >> I am trying to run a 2x2 ANOVA within subjects, N=22. Each subject had >> two levels (cue vs nonce) and two conditions (non treatment vs treatment). >> I am interesting in the main effects and possible interaction between them. >> I am not sure if the design matrix is correct or not, can anyone give me >> some feedback please? >> >> Many thanks! >> >> >> > >