A0658
Title: Robust inference on infinite and growing dimensional time series regression
Authors: Abhimanyu Gupta - University of Essex (United Kingdom) [presenting]
Myung Hwan Seo - Seoul National University (Korea, South)
Abstract: A class of tests for time series models, such as multiple regression with growing dimension, infinite-order autoregression and nonparametric sieve regression, are developed. Examples include the Chow test and general linear restriction tests of growing rank p. Employing such increasing p asymptotics, a new scale correction is introduced to conventional test statistics, which accounts for a high-order long-run variance (HLV) that emerges as p grows with sample size. A bias correction via a null-imposed bootstrap is also proposed to alleviate finite sample bias without sacrificing power. A simulation study shows the importance of robustifying testing procedures against the HLV even when p is moderate. The tests are illustrated with an application to the oil regressions in Hamilton (2003).