Conditional heteroskedasticity in nonlinear simultaneous equations

We show in this paper that the treatment of conditional heteroskedasticity inside nonlinear systems of simultaneous equations is a sufficiently manageable matter for some types of multivariate ARCH error structures. Reparameterization makes it possible to estimate the model by means of the (nearly) standard algorithms developed in the past and widely used for estimating nonlinear simultaneous equations where the error structure is of the i.i.d. type with unrestricted contemporaneous covariance matrix. The method is discussed in this paper and empirical applications exemplify the efficiency gains.