2
$\begingroup$

I am measuring the effect of fatigue in human movement. I measure a gait parameter before and after fatigue. I have tested 60 subjects. I have 5 measurements of the same parameter before and after fatigue. I measure 5 times because humans have a variability.

Which of these options would be better for my analysis?

  1. Calculate the mean of the 5 measurements, and apply a paired t-test. But this implies that I have only 60x2 samples. One before fatigue, one after fatigue.
  2. ANOVA mixed model. The fixed factor is fatigue (No-Yes). And the random factor is the subject.

I think that I should choose the ANOVA. With the ANOVA I have 5x60x2 samples. And more samples increase the power of the test. What do you think?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

I think you should use ANOVA mixed model. As far as I know, there are two main reasons for using it. First, by having more data points, the power of the analysis increases. Second, you can also take into account random variability due to subjects and measurements.

Improve this answer
$\endgroup$
0

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.