Predictive Inference for Locally Stationary Time Series With an Application to Climate Data
- 3 February 2020
- journal article
- research article
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 116 (534) , 919-934
Abstract
The model-free prediction principle of Politis has been successfully applied to general regression problems, as well as problems involving stationary time series. However, with long time series, for example, annual temperature measurements spanning over 100 years or daily financial returns spanning several years, it may be unrealistic to assume stationarity throughout the span of the dataset. In this article, we show how model-free prediction can be applied to handle time series that are only locally stationary, that is, they can be assumed to be stationary only over short time-windows. Surprisingly, there is little literature on point prediction for general locally stationary time series even in model-based setups, and there is no literature whatsoever on the construction of prediction intervals of locally stationary time series. We attempt to fill this gap here as well. Both one-step-ahead point predictors and prediction intervals are constructed, and the performance of model-free is compared to model-based prediction using models that incorporate a trend and/or heteroscedasticity. Both aspects of the article, model-free and model-based, are novel in the context of time-series that are locally (but not globally) stationary. We also demonstrate the application of our model-based and model-free prediction methods to speleothem climate data which exhibits local stationarity and show that our best model-free point prediction results outperform that obtained with the RAMPFIT algorithm previously used for analysis of this type of data. Supplementary materials for this article are available online.Keywords
All Related Versions
Funding Information
- NSF grant (DMS 12-23137, DMS 16-13026)
- NSF grant (ACI-1541349)
This publication has 25 references indexed in Scilit:
- Banded and tapered estimates for autocovariance matrices and the linear process bootstrapJournal of Time Series Analysis, 2010
- Simultaneous Inference of Linear Models with Time Varying CoefficientsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Local linear quantile estimation for nonstationary time seriesThe Annals of Statistics, 2009
- Holocene Forcing of the Indian Monsoon Recorded in a Stalagmite from Southern OmanScience, 2003
- Methods for Estimating a Conditional Distribution FunctionJournal of the American Statistical Association, 1999
- Fitting time series models to nonstationary processesThe Annals of Statistics, 1997
- BANDWIDTH SELECTION IN KERNEL SMOOTHING OF TIME SERIESJournal of Time Series Analysis, 1996
- Nonparametric Estimation and Identification of Nonlinear ARCH Time Series Strong Convergence and Asymptotic Normality: Strong Convergence and Asymptotic NormalityEconometric Theory, 1995
- The Stationary BootstrapJournal of the American Statistical Association, 1994
- KERNEL REGRESSION SMOOTHING OF TIME SERIESJournal of Time Series Analysis, 1992