Whittle Estimation of ARCH Models
Liudas Giraitis and Peter M Robinson
Published November 2000
For a class of parametric ARCH models, Whittle estimation based on squared observations is shown to be inconsistent and asymptotically normal. Our conditions require the squares to have short memory autocorrelation, by comparison with the work of Zaffaroni (1999), who established the same properties on the basis of an alternative class of models with martingale difference levels and long memory autocorrelated squares.
Paper Number EM/2000/406:
Download PDF - Whittle Estimation of ARCH Models