Sequential least squares estimate of linear parameters of ARCH process

Forguaranteed estimation of the parameters of a stable autoregressive process with heteroscedasticity ARCH(q) by the least squares method,the paper proposes to use a particular stopping rule which essentially depends on the behaviors of the minimal eigenvalue of the observedFisher information matrix. Asymptotic formulas for the upper bound of the mean square bias and mean of the stopping time are given.

Keywords

Authors

References