The PANEL procedure can fit models that have linear restrictions, producing a Lagrange multiplier (LM) test for each restriction. Consider a set of J linear restrictions , where
is
and
is
.
The restricted regression is performed by minimizing the error sum of squares subject to the restrictions. In matrix terms, the Lagrangian for this problem is
The Lagrangian is minimized by the restricted estimator , and it can be shown that
where is the unrestricted estimator.
Because , you can solve for
to obtain the Lagrange multipliers
The standard errors of the Lagrange multipliers are the square roots of the diagonal elements of the variance matrix
where is the mean square error (MSE) under the null hypothesis. A significant Lagrange multiplier indicates a restriction that is binding.