Pesaran, M.H. and Smith, Ron (2024) High dimensional forecasting with known knowns and known unknowns. National Institute Economic Review , ISSN 1741-3036.
|
Text
2024high-dimensional-forecasting-with-known-knowns-and-known-unknowns.pdf - Published Version of Record Download (1MB) | Preview |
Abstract
Forecasts play a central role in decision-making under uncertainty. After a brief review of the general issues, this article considers ways of using high-dimensional data in forecasting. We consider selecting variables from a known active set, known knowns, using Lasso and One Covariate at a time Multiple Testing, and approximating unobserved latent factors, known unknowns, by various means. This combines both sparse and dense approaches to forecasting. We demonstrate the various issues involved in variable selection in a high-dimensional setting with an application to forecasting UK inflation at different horizons over the period 2020q1–2023q1. This application shows both the power of parsimonious models and the importance of allowing for global variables.
Metadata
| Item Type: | Article |
|---|---|
| Keyword(s) / Subject(s): | forecasting, high-dimensional data, Lasso, OCMT, latent factors, principal components |
| School: | Birkbeck Faculties and Schools > Faculty of Business and Law > Birkbeck Business School |
| Research Centres and Institutes: | Applied Macroeconomics, Birkbeck Centre for |
| Depositing User: | Ron Smith |
| Date Deposited: | 05 Nov 2024 12:52 |
| Last Modified: | 05 Nov 2024 23:49 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/54459 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
