You are on page 1of 4

13/5/2020 Relationship between Coefficient of Determination & Squared Pearson Correlation Coefficient | Economic Theory Blog

Advertisements

REPORT THIS AD

Economic Theory Blog

ECONOMETRICS, STATISTICS

Relationship between Coefficient of


Determination & Squared Pearson Correlation
Coefficient

NOVEMBER 5, 2014 | AD | 18 COMMENTS


The usual way of interpreting the coefficient of determination is to see it as the percentage of
the variation of the dependent variable ( ) can be explained by our model. The exact
interpretation and derivation of the coefficient of determination can be found here
(h ps://economictheoryblog.wordpress.com/2014/11/05/the-coefficient-of-determination-latex-
r2/).

Another way of interpreting the coefficient of determination is to look at it as the Squared


Pearson Correlation Coefficient between the observed values and the fi ed values . In this
post we are going to prove that this is actually the case. For the proof we have to know the
following (taken from OLS theory and general statistics):

In the following we are going to see how to derive the coefficient of determination from the
the Squared Pearson Correlation Coefficient between the observed values and the fi ed
values .

https://economictheoryblog.com/2014/11/05/proof/ 1/4
13/5/2020 Relationship between Coefficient of Determination & Squared Pearson Correlation Coefficient | Economic Theory Blog

Advertisements

REPORT THIS AD
ECONOMETRICS STATISTICS

18 thoughts on “Relationship between Coefficient of


Determination & Squared Pearson Correlation
Coefficient”

1. Pingback: The Coefficient Of Determination or R2 | Economic Theory Blog


2. Immanuel says:

https://economictheoryblog.com/2014/11/05/proof/ 2/4
13/5/2020 Relationship between Coefficient of Determination & Squared Pearson Correlation Coefficient | Economic Theory Blog

DECEMBER 12, 2014 AT 2:24 PM


Thank you for this!

1. isidorebeautrelet says:
FEBRUARY 14, 2015 AT 8:41 AM
You are very welcome!

3. mark leeds says:


MAY 1, 2015 AT 1:46 PM
Hi Isidore: Do you know if the relation between the correlation coefficient R and r holds for
the regression model with ma(1) errors ? empirically I seem to find that it doesn’t hold. but I
wanted to make sure that my code didn’t have a bug. thanks for any wisdom and your blog.

1. isidorebeautrelet says:
MAY 2, 2015 AT 9:24 AM
Hi Mark! That is actually a very good question which unfortunately I cannot answer out
of the box. However, once I have some time I will look into it. So far my feeling is that the
second of the five bullet points (listed in the post), i.e. the covariance between the fi ed
values and the error term being equal to zero, is most likely violated. Generally I think if
you are able to show that all five bullet points hold for a ma(1) process, the relationship
between r2 and the correlation coefficient should hold as well.

Let me know if you find an answer to the question.


Cheers!

4. mark leeds says:


MAY 2, 2015 AT 2:30 PM
Thanks Isidore: What you pointf out is equivalent to the sums of squares decomposition
relation , SSETOT = SSREG + SSE, being true. So I think I should look for info on when that
decomposition holds in general. cov(y hat, e ) not being zero makes it not true so your pont
is a good one. Thanks and I’ll let you know if I find anything out about it.

5. student says:
SEPTEMBER 18, 2016 AT 10:34 PM
How did you get from covar(x,y) to covar(y’,y)?

1. ad says:
SEPTEMBER 19, 2016 AT 10:34 AM
Thank you for your comment. I am sorry, but I cannot really help you as I do not
understand to which equation you are referring to. If you could be more specific I might
be able to help.
Regards

6. kasper says:
DECEMBER 8, 2016 AT 7:51 PM
Hello, can you tell me what you do between the pictures, i don’t quite understand it

1. ad says:
DECEMBER 9, 2016 AT 3:38 PM
Hello, what do you mean by pictures?

https://economictheoryblog.com/2014/11/05/proof/ 3/4
13/5/2020 Relationship between Coefficient of Determination & Squared Pearson Correlation Coefficient | Economic Theory Blog

7. ze says:
MARCH 16, 2018 AT 6:40 PM
Thanks a lot for this. Maybe, one possible small typo is: ESS/TSS should be RSS/TSS? This is
true as the mean of y^hat is equal to the mean of y, as the mean of e_i is zero.

1. ad says:
MARCH 18, 2018 AT 7:52 AM
Thank you for your comment. EES stands for “Explained Sum of Squares”, whereas RSS
stands for the “Residual Sum of Squares”. Hence ESS/TSS is correct.

Best, ad

8. ze says:
MARCH 16, 2018 AT 6:44 PM
o sorry, I guess I was wrong as ESS is as “Explained SS” .

1. ad says:
MARCH 18, 2018 AT 7:51 AM
Exactly, ESS stands for “Explained Sum of Squares”. Best ad

9. simon rasmussen says:


AUGUST 25, 2018 AT 11:29 PM
Very interesting content – thanks!

For some reason I fail to see the intuition behind the second last line. Why can var(y^) be
said to be equal to ESS?
Does this have to do with the assumptions behind the y^ line? Coulnd’t there be variance in
this regression line which doesn’t contribute to explaining the variance in y?

I hope my question makes sense

1. ad says:
AUGUST 26, 2018 AT 5:36 AM
Hi, this is a very good question. I was to short on this point. I will adjust the post such
that it becomes more clear. The short answer is, plug in the variance equation two times
and cancels out. What remains are the sum of squared residuals.

Thanks for this comment.


ad

10. Olivia says:


DECEMBER 12, 2018 AT 9:34 AM
Thank you. I think there is some missing squares on the second last line, no? var(y) =
sum((yi-mean(y))^2)/n, and the same thing for the estimates.

1. ad says:
DECEMBER 17, 2018 AT 10:41 AM
Thank you for you comment. You are right, of course! I adjusted the post. Cheers, ad

This site uses Akismet to reduce spam. Learn how your comment data is processed.

https://economictheoryblog.com/2014/11/05/proof/ 4/4

You might also like