Suppose you are estimating a (multivariate) model with a parameter vector $\theta=(\theta_1,\dots,\theta_p)'$. You have two constraints in the model, and would like to test them with either the likelihood ratio (LR) test, the Wald (W) test or Lagrange multiplier (LM) test. You have the following two constraints: \begin{align} H_0:\begin{cases} \theta_1 = 0 \\ \theta_2 = \theta_3 \end{cases} \end{align}

I am trying to determine the degrees of freedom for the relevant test, but seem not to be able to find it. Is it equal to the number of constraints (2 in this case) or the number of constrained parameters (3 in this case)?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.