Econometric packages can run regressions where you can specify constraints on pa

Question

Econometric packages can run regressions where you can specify constraints on parameters. Unfortunately, these can typically only be linear restrictions such as 2 7 = 3. We will extensively analyze the least squares problem for such restricted models later, but how do you run a regression when you have an inequality constraint? Suppose in the previous example, you were told that the incentives were announced only in the middle of February, so we expect c3 c2 c1. Can you find the least squares estimates subject to this restriction?

Explanation / Answer

You can find the least squares estimators by using quadratic programming, solving by simplex method subject to this restriction.

Related Questions

Navigate

• Browse (All)
• Browse E
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.