A self-normalized approach to confidence interval construction in time series
Author:
- Xiaofeng ShaoXSXiaofeng Shao
Preprint
Abstract
We propose a new method to construct confidence intervals for quantities that are associated with a stationary time series, which avoids direct estimation of the asymptotic variances. Unlike the existing tuning-parameter-dependent approaches, our method has the attractive convenience of being free of choosing any user-chosen number or smoothing parameter. The interval is constructed on the basis of an asymptotically distribution-free self-normalized statistic, in which the normalizing matrix is computed using recursive estimates. Under mild conditions, we establish the theoretical validity of our method for a broad class of statistics that are functionals of the empirical distribution of fixed or growing dimension. From a practical point of view, our method is conceptually simple, easy to implement and can be readily used by the practitioner. Monte-Carlo simulations are conducted to compare the finite sample performance of the new method with those delivered by the normal approximation and the block bootstrap approach.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- BLOCK BOOTSTRAP HAC ROBUST TESTS: THE SOPHISTICATION OF THE NAIVE BOOTSTRAPEconometric Theory, 2011
- Robust M tests using kernel-based estimators with bandwidth equal to sample sizeEconomics Letters, 2007
- Long run variance estimation and robust regression testing using sharp origin kernels with no truncationJournal of Statistical Planning and Inference, 2007
- A NEW ASYMPTOTIC THEORY FOR HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTSEconometric Theory, 2005
- HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTING USING BANDWIDTH EQUAL TO SAMPLE SIZEEconometric Theory, 2002
- TESTING FOR ZERO AUTOCORRELATION IN THE PRESENCE OF STATISTICAL DEPENDENCEEconometric Theory, 2002
- MIXING AND MOMENT PROPERTIES OF VARIOUS GARCH AND STOCHASTIC VOLATILITY MODELSEconometric Theory, 2002
- Establishing conditions for the functional central limit theorem in nonlinear and semiparametric time series processesJournal of Econometrics, 2002
- Asymptotic normality of spectral estimatesJournal of Multivariate Analysis, 1985
- Some mixing properties of time series modelsStochastic Processes and their Applications, 1985