Asymptotic Theory for Iterated One-Step Huber-Skip Estimators
University of Copenhagen Economics Discussion Paper No. 11-29
17 Pages Posted: 3 Dec 2011
Date Written: December 2, 2011
Iterated one-step Huber-skip M-estimators are considered for regression problems. Each one-step estimator is a re-weighted least squares estimators with zero/one weights determined by the initial estimator and the data. The asymptotic theory is given for iteration of such estimators using a tightness argument. The results apply to stationary as well as non-stationary regression problems.
Keywords: Huber-skip, iteration, one-step M-estimators, unit roots
JEL Classification: C32
Suggested Citation: Suggested Citation