Article2001

Bootstrap-After-Bootstrap Prediction Intervals for Autoregressive Models

56 citations0/0 files storedJournal of Business and Economic Statistics

No readable copy stored yet — this record is metadata only.

Forecasting Techniques and Applications Monetary Policy and Economic Impact Statistical Methods and Inference

Abstract

The use of the Bonferroni prediction interval based on the bootstrap-after-bootstrap is proposed for autoregressive (AR) models. Monte Carlo simulations are conducted using a number of AR models including stationary, unit-root, and near-unit-root processes. The major finding is that the bootstrap-after-bootstrap provides a superior small-sample alternative to asymptotic and standard bootstrap prediction intervals. The latter are often too narrow, substantially underestimating future uncertainty, especially when the model has unit roots or near unit roots. Bootstrap-after-bootstrap prediction intervals are found to provide accurate and conservative assessment of future uncertainty under nearly all circumstances considered.

Citations in this library

Stored only when both papers are in the corpus — 56 citations exist upstream.

References

1982Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation 1998Evaluating Interval Forecasts 1993Introduction to Multiple Time Series Analysis 1986Forecasting With Bayesian Vector Autoregressions—Five Years of Experience 1998Small-sample Confidence Intervals for Impulse Response Functions 1986Forecasting with Bayesian Vector Autoregressions: Five Years of Experience 1988Bayesian skepticism on unit root econometrics 1993Calculating Interval Forecasts

Cited by

2010Beyond point forecasting: Evaluation of alternative prediction intervals for tourist arrivals 2013Empirical prediction intervals revisited 2004Bootstrap prediction intervals for autoregression using asymptotically mean-unbiased estimators

Imported from OpenAlex (CC0) — nothing here is generated.