0
$\begingroup$

.Hi, everybody

I have data that has 28 subjects involved in a crossover design study including 4 different treatments. The amount of variables is over 10000 (measured almost on the same scale)

In general, I can construct a 28x4x10000 tensor.

My question is whether I can use PARAFAC for such a structure or it is not really applicable for crossover study design?

Thank you!

Improve this question
$\endgroup$
4
  • $\begingroup$ What is your scientific goal? What are your measurements? $\endgroup$
    – eric_kernfeld
    Commented May 31, 2016 at 19:32
  • $\begingroup$ Scientific goal is to see if certain variables are specific for a diet. $\endgroup$
    – Kirill
    Commented Jun 2, 2016 at 9:29
  • $\begingroup$ How are your variable measured? Are they binary? $\endgroup$
    – eric_kernfeld
    Commented Jun 3, 2016 at 0:52
  • $\begingroup$ What do you mean by "specific for a diet"? Are they events that might only occur in response to that diet? Do they change in response to that diet? $\endgroup$
    – eric_kernfeld
    Commented Jun 3, 2016 at 1:03

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.