TY - JOUR
AU - Gorodnichenko, Yuriy
AU - Mikusheva, Anna
AU - Ng, Serena
TI - Estimators for Persistent and Possibly Non-Stationary Data with Classical Properties
JF - National Bureau of Economic Research Working Paper Series
VL - No. 17424
PY - 2011
Y2 - September 2011
DO - 10.3386/w17424
UR - http://www.nber.org/papers/w17424
L1 - http://www.nber.org/papers/w17424.pdf
N1 - Author contact info:
Yuriy Gorodnichenko
Department of Economics
530 Evans Hall #3880
University of California, Berkeley
Berkeley, CA 94720-3880
Tel: 510/643-0720
Fax: 510/642-6615
E-Mail: ygorodni@econ.berkeley.edu
Anna Mikusheva
MIT
E-Mail: amikushe@mit.edu
Serena Ng
Department of Economics
Columbia University
420 West 118th Street
New York, NY 10027
Tel: 212/854-5488
Fax: 212/854-3735
E-Mail: Serena.Ng@columbia.edu
AB - This paper considers a moments based non-linear estimator that is root-T consistent and uniformly asymptotically normal irrespective of the degree of persistence of the forcing process. These properties hold for linear autoregressive models, linear predictive regressions, as well as certain non-linear dynamic models. Asymptotic normality is obtained because the moments are chosen so that the objective function is uniformly bounded in probability and that a central limit theorem can be applied.
Critical values from the normal distribution can be used irrespective of the treatment of the deterministic terms. Simulations show that the estimates are precise, and the t-test has good size in the parameter region where the least squares estimates usually yield distorted inference.
ER -