Forecasting with equilibrium-correction models during structural breaks

When breaks occur, equilibrium-correction models (EqCMs) based on cointegration face forecasting problems. We investigate approaches to alleviate forecast failure following a location shift, including updating, intercept corrections, differencing, and estimating the future impact of an 'intern...

Cijeli opis

Bibliografski detalji
Glavni autori: Castle, J, Hendry, D, Fawcett, N
Format: Working paper
Izdano: University of Oxford 2008
_version_ 1826290445584433152
author Castle, J
Hendry, D
Fawcett, N
author_facet Castle, J
Hendry, D
Fawcett, N
author_sort Castle, J
collection OXFORD
description When breaks occur, equilibrium-correction models (EqCMs) based on cointegration face forecasting problems. We investigate approaches to alleviate forecast failure following a location shift, including updating, intercept corrections, differencing, and estimating the future impact of an 'internal' break during its progress. Although updating can lead to a loss of cointegration when an EqCM suffers an equilibrium-mean shift, we show that updating can help when collinearities are changed by an 'external' break and the EqCM itself remains constant. Both mechanistic corrections help compared to just retaining a pre-break estimated model, but an estimated model of the break process could outperform. Throughout, we apply the approaches to the much-studied example of EqCMs for UK M1, and compare with updating a learning function as the break evolves.
first_indexed 2024-03-07T02:44:18Z
format Working paper
id oxford-uuid:ab8455d8-9ed5-4561-b19f-b4dac1e1d5ee
institution University of Oxford
last_indexed 2024-03-07T02:44:18Z
publishDate 2008
publisher University of Oxford
record_format dspace
spelling oxford-uuid:ab8455d8-9ed5-4561-b19f-b4dac1e1d5ee2022-03-27T03:22:25ZForecasting with equilibrium-correction models during structural breaksWorking paperhttp://purl.org/coar/resource_type/c_8042uuid:ab8455d8-9ed5-4561-b19f-b4dac1e1d5eeSymplectic ElementsBulk import via SwordUniversity of Oxford2008Castle, JHendry, DFawcett, NWhen breaks occur, equilibrium-correction models (EqCMs) based on cointegration face forecasting problems. We investigate approaches to alleviate forecast failure following a location shift, including updating, intercept corrections, differencing, and estimating the future impact of an 'internal' break during its progress. Although updating can lead to a loss of cointegration when an EqCM suffers an equilibrium-mean shift, we show that updating can help when collinearities are changed by an 'external' break and the EqCM itself remains constant. Both mechanistic corrections help compared to just retaining a pre-break estimated model, but an estimated model of the break process could outperform. Throughout, we apply the approaches to the much-studied example of EqCMs for UK M1, and compare with updating a learning function as the break evolves.
spellingShingle Castle, J
Hendry, D
Fawcett, N
Forecasting with equilibrium-correction models during structural breaks
title Forecasting with equilibrium-correction models during structural breaks
title_full Forecasting with equilibrium-correction models during structural breaks
title_fullStr Forecasting with equilibrium-correction models during structural breaks
title_full_unstemmed Forecasting with equilibrium-correction models during structural breaks
title_short Forecasting with equilibrium-correction models during structural breaks
title_sort forecasting with equilibrium correction models during structural breaks
work_keys_str_mv AT castlej forecastingwithequilibriumcorrectionmodelsduringstructuralbreaks
AT hendryd forecastingwithequilibriumcorrectionmodelsduringstructuralbreaks
AT fawcettn forecastingwithequilibriumcorrectionmodelsduringstructuralbreaks