R help - Nov 2008 - in R when I get negative adjusted R^2 using "lm", what might be the problem?

This is a linear regression of Y onto factors...

If I take log of Y, and regress onto the factors, I got:

Multiple R-squared: 0.4023,     Adjusted R-squared: 0.2731

If I don't take log of Y, and directly regress Y onto the factors, I got:

Multiple R-squared: 0.1807,     Adjusted R-squared: -0.001112

Is this negative adjusted R^2 a problem?

What observation can I make here and what might be the problem?

Thanks!

And in the non-log case, all the previously significant coefficients
now became insignificant...

On Sun, Nov 9, 2008 at 5:36 PM, Michael <comtech.usa at gmail.com>
wrote:
> This is a linear regression of Y onto factors...
>
> If I take log of Y, and regress onto the factors, I got:
>
> Multiple R-squared: 0.4023,     Adjusted R-squared: 0.2731
>
> If I don't take log of Y, and directly regress Y onto the factors, I
got:
>
> Multiple R-squared: 0.1807,     Adjusted R-squared: -0.001112
>
> Is this negative adjusted R^2 a problem?
>
> What observation can I make here and what might be the problem?
>
> Thanks!
>

No problem, adjusted R-squared can be negative.  If there truly is no
relationship, then the adjusted R-squared should average to 0, so sometimes it
must be negative.  All of your R-squared and adjusted R-squared values suggest
that there is not much of a relationship (less without the transform).

--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at imail.org
801.408.8111

> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Michael
> Sent: Sunday, November 09, 2008 6:37 PM
> To: r-help
> Subject: [R] in R when I get negative adjusted R^2 using "lm",
what
> might be the problem?
>
> This is a linear regression of Y onto factors...
>
> If I take log of Y, and regress onto the factors, I got:
>
> Multiple R-squared: 0.4023,     Adjusted R-squared: 0.2731
>
> If I don't take log of Y, and directly regress Y onto the factors, I
> got:
>
> Multiple R-squared: 0.1807,     Adjusted R-squared: -0.001112
>
> Is this negative adjusted R^2 a problem?
>
> What observation can I make here and what might be the problem?
>
> Thanks!
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.

Greg Snow wrote:
> No problem, adjusted R-squared can be negative.  If there truly is no
relationship, then the adjusted R-squared should average to 0, so sometimes it
must be negative.  All of your R-squared and adjusted R-squared values suggest
that there is not much of a relationship (less without the transform).
Nevertheless, there remains the logical problem of a negative squared 
value.

In any case, given the relatively large difference between the R-square 
and the adjusted value, he probably has a relative large number of 
independent variables compared to the number of rows in the data set. 
And the dependent variable is probably quite skewed as well.

Tom