st: NON-LINEAR LEAST SQUARES ESTIMATION

[<Patrizio.SICARI@oecd.org>]

Dear all,

I Hope someone can help me with what follows..

I have the following specification, where UNR, OG and EPL stand for unemployment rate, output gap and employment protection legislation, respectively. My problem is that I would like to impose the two restrictions below for λ2 and λ3. These coefficients should actually be estimated as combination of coefficients pertaining to other RHS variables.

ΔUNR = αL(ΔUNR) + β1*ΔOG + β2*L(ΔOG) + β3*L2(ΔOG) + λ1*EPL_ΔOG + λ2*EPL_L(ΔOG) + λ3*EPL_L2(ΔOG)

With:   λ2 = λ1 * (β2/β1)                and  λ3 = λ1 * (β3/β1)


I have tried with both NL and CNSREG commands, but haven't been able to succeed, as I always end up with an error message. Can anyone give me advice?

Thanks in advance.

Patrizio

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/