Kerri (solan_t) wrote,
Kerri
solan_t

Pet peeve that just got stepped on.

Saying 'correlation coefficient (R2)' DOES NOT MAKE R^2 THE CORRELATION COEFFICIENT!!!!!!! No matter HOW HARD YOU TRY OR HOW OFTEN YOU REPEAT IT!


R is the correlation coefficient.
R^2 has a much longer (and more difficult to remember....) title!!!!!!!!

Why does this piss me off? Because I have had MULTIPLE instances of methods or protocols asking for the 'correlation coefficient' to be calculated and compared to a criteria... and strangely enough, I calculate the correlation coefficient and get told to recalculate it later, because, of course, these people really wanted R^2. Worse yet, if the correlation coefficient is actually NEGATIVE, I have trouble comparing it to a critera that really wanted R^2 (a positive number)

When they ask for 'correlation coefficient (R2)' I am left wondering which one they REALLY wanted.....
Subscribe
  • Post a new comment

    Error

    default userpic

    Your reply will be screened

    Your IP address will be recorded 

    When you submit the form an invisible reCAPTCHA check will be performed.
    You must follow the Privacy Policy and Google Terms of use.
  • 10 comments