0

I tried to do the friedman test to see if there are differences between my multiple measurements (OrderIntime, 5 different measurementtimes) over my 6 conditions (6 different SpeechRates SR). I measured correlations (in the brain) for 6 speech rates. For each speech rate I measured 5 times. And I have 20 subjects. However when I run the test: 

friedman.test(EnvTrackAll$correlation, EnvTrackAll$OrderInTime, EnvTrackAll$subject)

I get this error: 

Error in friedman.test.default(EnvTrackAll$correlation, EnvTrackAll$OrderInTime,  : 
  not an unreplicated complete block design

How do I transform my dataframe into an unreplicated complete block design? Due to ethical reasons I can’t share my dataframe, but it looks like this for example (where A is my first subject):

enter image description here

r2evans
  • 141,215
  • 6
  • 77
  • 149
Sofie55
  • 1
  • Look here: it may be about categorical variables. https://stackoverflow.com/questions/21457505/friedman-test-unreplicated-complete-block-design-error – sconfluentus Mar 25 '20 at 23:17
  • 1
    Please do not post an image of code/data/errors: it cannot be copied or searched (SEO), it breaks screen-readers, and it may not fit well on some mobile devices. Ref: https://meta.stackoverflow.com/a/285557/3358272 (and https://xkcd.com/2116/). Please just include the code, console output, or data (e.g., `dput(head(x))` or `data.frame(...)`) directly. And *yes*, I understand that the data is sensitive. If you can give an image of representative data, though, you can give (fake) representative data in a more-easily consumed format. – r2evans Mar 25 '20 at 23:18

0 Answers0