One of the three tests of restrictions on an unknown parameter, or a vector of unknown parameters, θ, based on the maximum likelihood estimation of θ (along with the likelihood ratio test and the Wald test). The null hypothesis is H0: λ = 0, where λ is the vector of Lagrange multipliers of the constrained maximization problem, in which the objective function is the log-likelihood function and the constraint is the set of restrictions. In an equivalent, simpler formulation, the LM test statistic is based on the derivatives of the log-likelihood function evaluated at θ̂R, the maximum likelihood estimator of θ obtained under restrictions. Under the null hypothesis the distribution of the LM test statistic has asymptotically chi-square distribution, with degrees of freedom equal to the number of restrictions.