Multi-step estimation for forecasting
The authors delineate conditions which favor multistep, or dynamic, estimation for multistep forecasting. An analytical example shows how dynamic estimation may accommodate incorrectly specified models as the forecast lead alters, improving forecast performance for some misspecifications. However, i...
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Blackwell Publishers
1996
|
| _version_ | 1826259739794735104 |
|---|---|
| author | Clements, M Hendry, D |
| author_facet | Clements, M Hendry, D |
| author_sort | Clements, M |
| collection | OXFORD |
| description | The authors delineate conditions which favor multistep, or dynamic, estimation for multistep forecasting. An analytical example shows how dynamic estimation may accommodate incorrectly specified models as the forecast lead alters, improving forecast performance for some misspecifications. However, in correctly specified models, reducing finite-sample biases does not justify dynamic estimation. In a Monte Carlo forecasting study for integrated processes, estimating a unit root in the presence of a neglected negative moving-average error may favor dynamic estimation, though other solutions exist to that scenario. A second Monte Carlo study obtains the estimator biases and explains those using asymptotic approximations. |
| first_indexed | 2024-03-06T18:54:33Z |
| format | Journal article |
| id | oxford-uuid:115ccfae-5fbd-4756-b0a6-eff0ea0a5b31 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T18:54:33Z |
| publishDate | 1996 |
| publisher | Blackwell Publishers |
| record_format | dspace |
| spelling | oxford-uuid:115ccfae-5fbd-4756-b0a6-eff0ea0a5b312022-03-26T10:02:00ZMulti-step estimation for forecastingJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:115ccfae-5fbd-4756-b0a6-eff0ea0a5b31EnglishDepartment of Economics - ePrintsBlackwell Publishers1996Clements, MHendry, DThe authors delineate conditions which favor multistep, or dynamic, estimation for multistep forecasting. An analytical example shows how dynamic estimation may accommodate incorrectly specified models as the forecast lead alters, improving forecast performance for some misspecifications. However, in correctly specified models, reducing finite-sample biases does not justify dynamic estimation. In a Monte Carlo forecasting study for integrated processes, estimating a unit root in the presence of a neglected negative moving-average error may favor dynamic estimation, though other solutions exist to that scenario. A second Monte Carlo study obtains the estimator biases and explains those using asymptotic approximations. |
| spellingShingle | Clements, M Hendry, D Multi-step estimation for forecasting |
| title | Multi-step estimation for forecasting |
| title_full | Multi-step estimation for forecasting |
| title_fullStr | Multi-step estimation for forecasting |
| title_full_unstemmed | Multi-step estimation for forecasting |
| title_short | Multi-step estimation for forecasting |
| title_sort | multi step estimation for forecasting |
| work_keys_str_mv | AT clementsm multistepestimationforforecasting AT hendryd multistepestimationforforecasting |