[R-sig-Geo] Nagelkerke value for OLS model

Seyed Jalil Alavi sja_sari at yahoo.com
Mon Aug 31 07:20:54 CEST 2015

Dear all,
I would like to compare the performance of linear regression model with SAR models. One of the measures that I want to use is R squared.
Prof. Roger Bivand mentioned in r-sig-geo that "There is no direct equivalent to the OLS R-squared, these models are fitted by maximum likelihood. If you want something like an R-squared, try the Nagelkerke R-bar-squared, based on the likelihood. You should then compare this with a Nagelkerke value for your OLS model".
My question is:
How can I calculate a Nagelkerke value for OLS in R and compare it with Nagelkerke value form summary function in SAR Models.
Thank you so much
	[[alternative HTML version deleted]]

More information about the R-sig-Geo mailing list