Re: [Gretl-users] R-squared and the constant term (OLS)
On Wed, 23 Sep 2009, Henrique wrote:
But I have another doubt: What about the adjusted R^2? How Gretl
computes it (in the "no intercept" case)?
<script>
open data4-1
ols price sqft bedrms
X = $ess/(sum(price^2))
R2 = 1 - X
n = $T
k = $ncoeff
Rbar2 = 1 - (n-1)/(n-k) * X
</script>
Allin.