## adjusted R-squared in PROC GLM

Frequent Contributor
Posts: 130

# adjusted R-squared in PROC GLM

PROC GLM DATA=have ;

ABSORB year;

MODEL y = a b c /solution noint ;

RUN;

QUIT;

Super Contributor
Posts: 490

## Re: adjusted R-squared in PROC GLM

I do not think there is such option why do not you use PROC RSQUARE

Frequent Contributor
Posts: 130

## Re: adjusted R-squared in PROC GLM

Thank you Mohamed!

Posts: 2,655

## Re: adjusted R-squared in PROC GLM

A couple of points: R squared and adjusted R squared are oddly defined with models without intercepts.  Still, you could plug the R-squared value obtained from GLM into the formula for adjusted R squared (no intercept):

ADJRSQ(no int) = 1 - n * (1 - R^2)/(n - p), where n is the number of observations and p is the number of parameters fit.

Steve Denham

Frequent Contributor
Posts: 130

## Re: adjusted R-squared in PROC GLM

Thank you Steve! that's very helpful.

Frequent Contributor
Posts: 122

## Re: adjusted R-squared in PROC GLM

Steve et al.,

It was not clear to me if the model the R^2 value came from had to have any type of option in regards to the intercept or not. Do I run a normal proc glm when getting the R^2 value for the calculation. Also, do you know the name of this particular R^2 adjustment?

Thanks!

Frequent Contributor
Posts: 122

## Re: adjusted R-squared in PROC GLM

I didn't see a "-1" in the df line, so I am guessing the "noint" option needs to be used with the proc glm statement that generates the R^2, correct?

Frequent Contributor
Posts: 122

## Re: adjusted R-squared in PROC GLM

Sidenote, I get this in my Log:

"NOTE: Due to the presence of CLASS variables, an intercept is implicitly fitted. R-Square has

been corrected for the mean."

Posts: 2,655

## Re: adjusted R-squared in PROC GLM

The formula I gave for the adjusted R^2 is just the standard adjustment, except that the n-1 in the numerator and denominator is replaced by n, since the intercept is not estimated.  I don't remember where I found that, but Draper and Smith would be a good place to start. It needs to be the value obtained with the noint option, for it to be consistent.  It is a measure of the association between the response and the X values, both considered as deviations from zero, rather than deviations from the mean.

Steve Denham

Discussion stats
• 8 replies
• 6095 views
• 3 likes
• 4 in conversation