A Generalized Variance Bounds Test

Abstract

This paper derives a variance bounds test for a broad class of linear rational expectations models. According to this test, if observed data accord with the model, then a weighted sum of auto-covariances of the covariance-stationary components of the endogenous state variables should be nonnegative. The new test reinterprets West’s (1986) variance bounds test and extends its applicability by not requiring observable exogenous state variables, covariance-stationary exogenous or endogenous state variables, or a zero initial value for the endogenous state variable. The paper also discusses the possibility of the new test’s application to nonlinear models.

---