On the constancy of time-series econometric equations
Parameter constancy is a fundamental requirement for empirical models to be useful for forecasting, analysing economic policy, or testing economic theories. However, there are surprises in defining a constant-parameter model, such that models with time-varying coefficients, and expansion of the para...
Main Author: | |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Economic & Social Research Institute
1996
|
_version_ | 1797095551196463104 |
---|---|
author | Hendry, D |
author_facet | Hendry, D |
author_sort | Hendry, D |
collection | OXFORD |
description | Parameter constancy is a fundamental requirement for empirical models to be useful for forecasting, analysing economic policy, or testing economic theories. However, there are surprises in defining a constant-parameter model, such that models with time-varying coefficients, and expansion of the parameterisation over time are both compatible with constancy, yet unbiased forecasts may not entail a sensible model choice. In-sample tests cannot determine likely post-sample predictive failure. A comparison of two models of UK money demand illustrates the analysis empirically, as one suffers considerable predictive failure yet the other does not, despite being identical in-sample. |
first_indexed | 2024-03-07T04:29:28Z |
format | Journal article |
id | oxford-uuid:cdd32c72-7739-4409-a368-4e72b428526e |
institution | University of Oxford |
language | English |
last_indexed | 2024-03-07T04:29:28Z |
publishDate | 1996 |
publisher | Economic & Social Research Institute |
record_format | dspace |
spelling | oxford-uuid:cdd32c72-7739-4409-a368-4e72b428526e2022-03-27T07:31:21ZOn the constancy of time-series econometric equationsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:cdd32c72-7739-4409-a368-4e72b428526eEnglishDepartment of Economics - ePrintsEconomic & Social Research Institute1996Hendry, DParameter constancy is a fundamental requirement for empirical models to be useful for forecasting, analysing economic policy, or testing economic theories. However, there are surprises in defining a constant-parameter model, such that models with time-varying coefficients, and expansion of the parameterisation over time are both compatible with constancy, yet unbiased forecasts may not entail a sensible model choice. In-sample tests cannot determine likely post-sample predictive failure. A comparison of two models of UK money demand illustrates the analysis empirically, as one suffers considerable predictive failure yet the other does not, despite being identical in-sample. |
spellingShingle | Hendry, D On the constancy of time-series econometric equations |
title | On the constancy of time-series econometric equations |
title_full | On the constancy of time-series econometric equations |
title_fullStr | On the constancy of time-series econometric equations |
title_full_unstemmed | On the constancy of time-series econometric equations |
title_short | On the constancy of time-series econometric equations |
title_sort | on the constancy of time series econometric equations |
work_keys_str_mv | AT hendryd ontheconstancyoftimeserieseconometricequations |