A comparison of the forecast performance of Markov‐switching and threshold autoregressive models of US GNP

DOI10.1111/1368-423x.11004OpenAlexW1964743509MaRDI QIDQ6166852

Hans-Martin Krolzig, Michael P. Clements

Publication date: 7 July 2023

Published in: The Econometrics Journal (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1111/1368-423x.11004

zbMATH Keywords

predictionbusiness cyclesregime shiftsMonte Carlo simulationnonlinear time series

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (13)

Contemporaneous threshold autoregressive models: estimation, testing and forecasting ⋮ Testing for a Markov-Switching Mean in Serially Correlated Data ⋮ Nonlinear Time Series Models and Model Selection ⋮ Real-time factor model forecasting and the effects of instability ⋮ Partially hidden Markov chain multivariate linear autoregressive model: inference and forecasting -- application to machine health prognostics ⋮ Information criteria for nonlinear time series models ⋮ The convergence of optimization based GARCH estimators: theory and application ⋮ Forecasting Markov-switching dynamic, conditionally heteroscedastic processes ⋮ Forecasting with univariate TAR models ⋮ Long memory and regime switching ⋮ Can nonlinear time series models generate US business cycle asymmetric shape? ⋮ A nonlinear long memory model, with an application to US unemployment. ⋮ Semiparametric transition models

This page was built for publication: A comparison of the forecast performance of Markov‐switching and threshold autoregressive models of US GNP