Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: st: about residuals and coefficients
From
Heng Lu <[email protected]>
To
Richard Williams <[email protected]>, "[email protected]" <[email protected]>
Subject
RE: st: about residuals and coefficients
Date
Mon, 2 Sep 2013 05:17:29 -0700
Hi,
For your first question, you should look at the semi-partial r square
for x1 and x2.
You put both x1 and x2 into model, get a r-square 1.
You put x1 into model only, get a r-square 2.
You put x2 into model only, get a r-square 3.
The semi-partial r square for x1 is r-square 1 - r-square 3, that's the
contribution brought about by x1.
The semi-partial r square for x2 is r-square 1 - r-square 2.
Please google semi-partial r square for more information.
Regards,
Lu Heng
From: Richard Williams
Sent: 2013/9/2 19:56
To: [email protected]
Subject: Re: st: about residuals and coefficients
At 04:57 AM 9/2/2013, Kayla Bridge wrote:
>Dear all,
>I am currently running a simple regression, and try to explain the
>coefficients. The model and estimation results are the following.
>y=5.41+1.24*x1+.28*x2, R2=0.7, N=20
> (0.58) (3.4) (2.56)
>The t-stats are in parentheses.
>I'd like to know how much (in terms of percentage) of the change in
>y is accounted for by change in x1, and how much change in y by change in x2.
Unless x1 and x2 are uncorrelated, you can't say something like x1
accounts for 40% and x2 accounts for 60%. I'm guessing -pcorr- comes
closest to what you want. Read the manual entry as it is much more
detailed than the program help.
>Another question is: can I use [sum(residual^2)]/[sum((y-ybar)^2)],
>where ybar is the mean value of the dependent variable, to say
>something about percentage of residual, like smaller percentage of
>residuals implies that x1 and x2 are good explanatory factors for y?
Why don't you just use R^2? I could be wrong, but your formula looks
like 1 - R^2.
>Any suggestion is greatly appreciated.
>Best,
>Kayla
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/