A note on the validity of cross-validation for evaluating autoregressive time series prediction

DOI10.1016/j.csda.2017.11.003zbMath1469.62021OpenAlexW2770188460MaRDI QIDQ138202

Christoph Bergmeir, Rob J. Hyndman, Bonsoo Koo, Rob Hyndman, Bonsoo Koo, Christoph Bergmeir

Publication date: April 2018

Published in: Computational Statistics & Data Analysis, Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2017.11.003

zbMATH Keywords

time seriescross-validationautoregression

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Inference from stochastic processes and prediction (62M20) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Related Items (16)

Two filtering methods of forecasting linear and nonlinear dynamics of intensive longitudinal data ⋮ A GROUP REGULARISATION APPROACH FOR CONSTRUCTING GENERALISED AGE-PERIOD-COHORT MORTALITY PROJECTION MODELS ⋮ POINT AND INTERVAL FORECASTS OF DEATH RATES USING NEURAL NETWORKS ⋮ Trading Signals in VIX Futures ⋮ Efficient use of data for LSTM mortality forecasting ⋮ Estimating large‐dimensional connectedness tables: The great moderation through the lens of sectoral spillovers ⋮ Time series cross validation: a theoretical result and finite sample performance ⋮ Clustering nonlinear time series with neural network bootstrap forecast distributions ⋮ Penalized Estimation and Forecasting of Multiple Subject Intensive Longitudinal Data ⋮ Using shared sell-through data to forecast wholesaler demand in multi-echelon supply chains ⋮ The MELBS team winning entry for the EVA2017 competition for spatiotemporal prediction of extreme rainfall using generalized extreme value quantiles ⋮ Imputation of clinical covariates in time series ⋮ forecastML ⋮ Long-term real dynamic investment planning ⋮ Generative adversarial networks for financial trading strategies fine-tuning and combination ⋮ From zero to hero: realized partial (co)variances

Uses Software

• R
• expsmooth
• forecastML

Cites Work

• Unnamed Item
• Unnamed Item
• Forecasting with exponential smoothing. The state space approach
• A survey of cross-validation procedures for model selection
• Mixing properties of ARMA processes
• Nonparametric curve estimation from time series
• Time series: theory and methods.
• Nonparametric regression with correlated errors.
• Consistent cross-validatory model-selection for dependent data: hv-block cross-validation
• On the usefulness of cross-validation for directional forecast evaluation
• Measuring the prediction error. A comparison of cross-validation, bootstrap and covariance penalty methods
• Consistency in Nonlinear Econometric Models: A Generic Uniform Law of Large Numbers
• DATA-DEPENDENT ESTIMATION OF PREDICTION FUNCTIONS
• On a measure of lack of fit in time series models
• A cross-validatory method for dependent data

This page was built for publication: A note on the validity of cross-validation for evaluating autoregressive time series prediction