st: second order serial correlation with no restrictions (i.e, rho2 notconstrained by rho1)

[TSchatzki@lecg.com]

Does anyone know how to do second order serial correlation where the rho's
are not constrained. i.e.

e(t) = rho1*e(t-1) + rho2*e(t-2) + u(t)

where rho2 ~= rho1^2

I'm interested in the case of an otherwise linear regression

thanks, Todd


Todd Schatzki
LECG
350 Massachusetts Avenue, Suite 300
Cambridge, MA  02139
617-761-0114
617-621-8018 (fax)


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/