TY - JOUR
T1 - Two-Step And Related Estimators In Contemporary Rational-Expectations Models
T2 - An Analysis Of Small-Sample Properties
AU - Hoffman, Dennis
N1 - Funding Information:
This research is supported by National Science Foundation grant SES-8420465 and the Summer Research Program at Arizona State University. I thank Adrian Pagan, Hashem Pesaran, Peter Schmidt, Mike Ormis-ton, Don Schlagenhauf, Stuart Low, and Michael Veal1 for their comments. Stephen Norrbin deserves credit for his programming expertise in producing early versions of this article.
PY - 1991/1
Y1 - 1991/1
N2 - This article examines the performance of ordinary least squares, generalized least squares, and Pagan’s (1986) double-length estimator (DLE) in several rational-expectations models. The three approaches are equivalent in the simplest of models but may differ appreciably in models typically encountered in applied work. Small-sample properties of the estimators are examined in several contemporary macroeconomic models. The following conclusions are reached: (a) All estimators exhibit similar sampling distributions in a monetary-neutrality framework, (b) the least squares procedures maintain smaller sampling variance and deliver more reliable tests in a permanent- income model in very small samples, (c) DLE generally delivers superior performance in a nonlinear aggregate-supply model with unanticipated “shock” regressors, and (d) overall, DLE outperforms the LS alternatives except in the smallest of samples.
AB - This article examines the performance of ordinary least squares, generalized least squares, and Pagan’s (1986) double-length estimator (DLE) in several rational-expectations models. The three approaches are equivalent in the simplest of models but may differ appreciably in models typically encountered in applied work. Small-sample properties of the estimators are examined in several contemporary macroeconomic models. The following conclusions are reached: (a) All estimators exhibit similar sampling distributions in a monetary-neutrality framework, (b) the least squares procedures maintain smaller sampling variance and deliver more reliable tests in a permanent- income model in very small samples, (c) DLE generally delivers superior performance in a nonlinear aggregate-supply model with unanticipated “shock” regressors, and (d) overall, DLE outperforms the LS alternatives except in the smallest of samples.
KW - Generalized least squares
KW - Generated regressors
KW - Monte Carlo simulation
KW - Nonlinear estimation
UR - http://www.scopus.com/inward/record.url?scp=8344286916&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=8344286916&partnerID=8YFLogxK
U2 - 10.1080/07350015.1991.10509826
DO - 10.1080/07350015.1991.10509826
M3 - Article
AN - SCOPUS:8344286916
SN - 0735-0015
VL - 9
SP - 51
EP - 61
JO - Journal of Business and Economic Statistics
JF - Journal of Business and Economic Statistics
IS - 1
ER -