As mentioned in the title I have an unbalanced repeated measures data set and would like to calculate the correlation of a particular stat with win percentage. The data set is of player performances where players may have repeated observations and the number of times a player can appear is not set. I have done some research and found that using a mixed effect linear model is the best way to go about this, which will control for the impact of the player,

enter image description here enter image description here

My main goal is to calculate the correlation between the 'Statistic' and Win%, do the results of this test give me some advice on what type of correlation test to use? Does this test tell me how significant the different player groups are? If they aren't significant am I then able to use a pearson correlation on the data set?

This is an example of my data, 3 columns


enter image description here

Any help is greatly appreciated.

Thank you

  • $\begingroup$ You have "an unbiased repeated measures data set". Could you give an example of "biased repeated measures data set"? $\endgroup$ – user158565 Mar 29 at 3:32
  • $\begingroup$ sorry user158565 I meant to say unbalanced instead of unbiased. In my case this means that the number of performances per player is not the same $\endgroup$ – George Mar 29 at 13:51

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.