05-08-2018 01:13 AM - edited 05-09-2018 04:51 AM
I want to test for heteroskedasticity and autocorrelation in a large unbalanced panel dataset.
I do so using the following code for running regrresion
ods html; Proc glm DATA=Sampledata; class time firm date; model volume = time firm date/ NOINT solution; run;
All explanatory variables are dummies. However, variables, which are calculated, are more than 2000.
What is the faster program or procedure perform these tests?
Thanks in advance.