Skip to content
Prev 8088 / 29559 Next

Lagrange multiplier tests for weighted least squares

On Wed, 21 Apr 2010, Roberto Patuelli wrote:

            
I think econometricians, spatial or not, typically do not "do" weights, 
but prefer to use HAC or similar standard errors. LM tests are fro the 
spatial econometrics approach, so they do not accommodate weights. To add 
them would mean doing the math to see where in the development the omega 
should be added into the spatial process, then one would need to show that 
the tests perform as expected. Nice paper if one had time!

Roger