Posted by Jian on March 12, 2001 at 13:44:28:
In Reply to: Re: t-test on time series data posted by B. Douglas Ward on March 09, 2001 at 11:21:36:
Hi, Doug. Thank you for your response, I still have some
questions here, thank you for your patient.
1. if I use 3dfim+ (include Fit Coef, Best Index, % Change and
Correlation) and get a buck file for several runs seperately
within subject, then I should use 3dTcat to concatenate the
runs within one subject, should I need use -rlt, I think Fim +
have done it for me. See I use toTcat -prefix tcat -session . run1
run2 run3, then I can get a tcat file, then I do tlrc, then use
it to do ttest between subjects, does that make sense.
2. If I use Deconvolution, I can also do it like the way mentioned
above, except after concatenate, I have to use -concat option
for deconvolution.
3. If I have two data sets and the time point is different, see
there are 96 time points for set1 and 128 time point for set2,
can I use t-test or other statistica method of AFNI to compare
the two datasets after I have concatenate each runs for different
subjects.
Thanks