Sign in
Back
Weighted least squares-based inference for stable and unstable threshold power ARCH processes
Journal article   Peer reviewed

Weighted least squares-based inference for stable and unstable threshold power ARCH processes

Abdelhakim Aknouche and Nassim Touche
Statistics & probability letters, Vol.97, pp.108-115
02/2015
DOI: https://doi.org/10.1016/j.spl.2014.11.011

Abstract

Consistency and asymptotic normality Heavy tailed distribution Strict stationarity testing Threshold power [formula omitted] Two-stage weighted least squares
We establish consistency and asymptotic normality for a weighted least squares estimate (2SWLSE) of a threshold power ARCH process in both stationary and nonstationary environments. For models with heavy tail innovations, the 2SWLSE is more efficient than the quasi-maximum likelihood estimate.

Metrics

1 Record Views

Details