期刊名称：Cardiff Economics Working Papers / Cardiff University, Cardiff Business School
印刷版ISSN：1749-6101
出版年度：2021
期号：35
语种：English
出版社：Cardiff University
摘要：The purpose of this paper is to investigate the empirical performance of the standard New Keynesian dynamic stochastic general equilibrium (DSGE) model in its usual form with full-information rational expectations and compare it with versions assuming inattentiveness- namely sticky information and imperfect information data revision. Using a Bayesian estimation approach on US quarterly data (both realtime and survey) from 1969 to 2015, we find that the model with sticky information fits best and is the only one that can generate the delayed responses observed in the data. The imperfect information data revision model is improved fits better when survey data is used in place of real-time data, suggesting that it contains extra information.
关键词：Forecasting Popular Votes Shares;Electoral Poll;Forecast combination;Hybrid model;Support Vector Machine
