A simple recursive forecasting model

被引：124
作者：
Branch, William A.
Evans, George W.
机构：
[1] Univ Oregon, Dept Econ, Eugene, OR 97403 USA
[2] Univ Calif Irvine, Irvine, CA 92717 USA
来源：
ECONOMICS LETTERS | 2006年 / 91卷 / 02期
关键词：
constant gain; recursive learning; expectations;
D O I：
10.1016/j.econlet.2005.09.005
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
We compare the performance of alternative recursive forecasting models. A simple constant gain algorithm, used widely in the learning literature, both forecasts well out of sample and also provides the best fit to the Survey of Professional Forecasters. (c) 2005 Elsevier B.V. All rights reserved.
引用
收藏
页码：158 / 166
页数：9
相关论文
共 23 条
  • [1] BRANCH WA, 2005, UNPUB MODEL UNCERTAI
  • [2] BULLARD J, 2004, 2004016A FED RES BAN
  • [3] BULLARD J, IN PRESS J EC DYNAMI
  • [4] Escaping Nash inflation
    Cho, IK
    Williams, N
    Sargent, TJ
    [J]. REVIEW OF ECONOMIC STUDIES, 2002, 69 (01) : 1 - 40
  • [5] CHO IK, 2002, LEARNING DYNAMICS EN
  • [6] Drifts and volatilities: monetary policies and outcomes in the post WWIIUS
    Cogley, T
    Sargent, TJ
    [J]. REVIEW OF ECONOMIC DYNAMICS, 2005, 8 (02) : 262 - 302
  • [7] Doan T., 1984, ECON REV, V3, P1, DOI DOI 10.1080/07474938408800053
  • [8] Policy interaction, expectations and the liquidity trap
    Evans, GW
    Honkapohja, S
    [J]. REVIEW OF ECONOMIC DYNAMICS, 2005, 8 (02) : 303 - 323
  • [9] EVANS GW, IN PRESS J MONETARY
  • [10] Hamilton J. D., 1994, TIME SERIES ANAL
123