Testing constancy of the error covariance matrix in vector models

This paper contains a Lagrange multiplier test of the hypothesis that the covariance matrix of a multivariate time series model is constant over time. It is further assumed that under the alternative, the error variances are time-varying whereas the correlation remain constant over time. Under the parameterized alternative hypothesis the variance may change continuously as a function of time or some observable stochastic variables.error covariance structure; Lagrange multiplier test; model misspecification; Monte Carlo simulation