1
$\begingroup$

Let's assume that we have 2 people and 5 objects with the following ratings (scale 1-5):

John has rated obj1:5, obj2:1 , obj3:(unknown value), obj4:2 , obj5:2 and Jack has rated obj1:1, obj2:5 , obj3:2, obj4:5 , obj5:5. Do i need obj3:2 when calculating the mean of Jack's ratings or just hypothetically delete it and use the other objects that have been rated by both of them? I want to calculate Pearson correlation between John and Jack. Also, i know that the obj3 will not be used in Pearson correlation function.

Thank you for your time.

$\endgroup$

closed as unclear what you're asking by Peter Flom Sep 22 '17 at 16:54

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

1
$\begingroup$

Yes, we do need to know all of Jack's ratings to calculate their mean.

And we need John's rating for object 3 to calculate correlation between John and Jack's ratings.

However, if Jack's rating for object 3 were equal to the mean of all of other Jack's ratings (which it is not), then we could calculate Pearson's correlation without knowing John's rating for object 3. You can look at the formula for covariance to see the reason.

$\endgroup$
  • 1
    $\begingroup$ Yes, because the subtraction will be zero. Thank you very much! $\endgroup$ – George Gkekas Sep 22 '17 at 18:32

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