1
$\begingroup$
>          day1      day2      day3      day4       day5     day6
>          [,1]      [,2]      [,3]      [,4]      [,5]      [,6] 
Round1[1,] 1.1207018 0.9727621 0.8193898 0.7632462 0.7999830 0.5990948 
Round2[2,] 0.8691757 1.0327617 0.9073291 0.8068437 0.8067108 0.6849726 
Round3[3,] 0.9204398 0.9728258 0.8829158 0.7979679 0.7517258 0.6474946 
Round4[4,] 1.0180250 0.9232659 0.9483964 0.8013724 0.6599834 0.6239292 
Round5[5,] 1.0481627 0.9085355 0.8098388 0.8491411 0.7670144 0.6623544 
Round6[6,] 1.0158818 0.9829552 0.7984692 0.8601835 0.6692525 0.7082392
> >

For 6 days, participants participate on experiment on which they have to answer through mouse. The value in the Matrix are the means of response time every round.

I'm wondering, through such kind of data if it's possible to demonstrate which of the following : the effect of habituation or fatigue, have more impact on response time, between rounds, between days and between participant.

What type of analysis should I use in this case ?

$\endgroup$

1 Answer 1

0
$\begingroup$

You can use multilevel modelling.

I assume you the matrix you showed in your example is data for one particular participant and you have the data like that for individuals in your study (not only average values).

If that is the case, you can treat rounds (or repeated measures), days, and participants as different levels of variation of the response time. Different participants have different response time, but if there is some indication of either habituation or fatigue, you should also see additional significant effect of either day or round, respectively.

$\endgroup$

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.