Print

Print
The t-test can only compare one or two levels of a single factor. Thus, you are limited to: one-sample test (one level of one factor against 0), two-sample t-test (one level compared to another level of one factor, levels are from different subjects), and paired t-test (one level compared to another level of one factor, levels are from the same subjects.

For group*time (2 factors), you need an ANOVA model. For repeated-measures (e.g. time or condition), you need to use the flexible factorial model. Only the effect of the repeated-measure factor and interactions with the repeated-measure factor will be valid in this model.

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 12, 2014 at 9:13 PM, Ben Hung <[log in to unmask]> wrote:
Dear SPM experts,

I’m now using sad and neutral face processing in my study, according to the SPM8 processingman(p.21), contrasts selected should be a comparison at the 1st level such as S>N in my study, for paired t test and 2 sample t test, group-by-time interaction seems not feasible in t tests, will this lead to any bias in the final data? Could I compare S>N contrast and conduct group-by-time interaction by using flexible factorial design?

Any advice will be much appreciated.

Best regards,
Ben Hung
LKS Faculty of Medicine
The University of Hong Kong