Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ...
We use "glide charts" (plots of sequences of root mean squared forecast errors as the target date is approached) to evaluate and compare fixed-target forecasts of Arctic sea ice. We first use them to evaluate the simple feature-engineered linear regression (FELR) forecasts of Diebold and G...
| Main Authors: | , , |
|---|---|
| Format: | Report |
| Language: | unknown |
| Published: |
arXiv
2022
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2206.10721 https://arxiv.org/abs/2206.10721 |
| _version_ | 1821821934414856192 |
|---|---|
| author | Diebold, Francis X. Goebel, Maximilian Coulombe, Philippe Goulet |
| author_facet | Diebold, Francis X. Goebel, Maximilian Coulombe, Philippe Goulet |
| author_sort | Diebold, Francis X. |
| collection | DataCite |
| description | We use "glide charts" (plots of sequences of root mean squared forecast errors as the target date is approached) to evaluate and compare fixed-target forecasts of Arctic sea ice. We first use them to evaluate the simple feature-engineered linear regression (FELR) forecasts of Diebold and Goebel (2021), and to compare FELR forecasts to naive pure-trend benchmark forecasts. Then we introduce a much more sophisticated feature-engineered machine learning (FEML) model, and we use glide charts to evaluate FEML forecasts and compare them to a FELR benchmark. Our substantive results include the frequent appearance of predictability thresholds, which differ across months, meaning that accuracy initially fails to improve as the target date is approached but then increases progressively once a threshold lead time is crossed. Also, we find that FEML can improve appreciably over FELR when forecasting "turning point" months in the annual cycle at horizons of one to three months ahead. ... |
| format | Report |
| genre | Arctic Sea ice |
| genre_facet | Arctic Sea ice |
| geographic | Arctic |
| geographic_facet | Arctic |
| id | ftdatacite:10.48550/arxiv.2206.10721 |
| institution | Open Polar |
| language | unknown |
| op_collection_id | ftdatacite |
| op_doi | https://doi.org/10.48550/arxiv.2206.10721 |
| op_rights | arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
| publishDate | 2022 |
| publisher | arXiv |
| record_format | openpolar |
| spelling | ftdatacite:10.48550/arxiv.2206.10721 2025-01-16T20:26:58+00:00 Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... Diebold, Francis X. Goebel, Maximilian Coulombe, Philippe Goulet 2022 https://dx.doi.org/10.48550/arxiv.2206.10721 https://arxiv.org/abs/2206.10721 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Econometrics econ.EM Applications stat.AP FOS Economics and business FOS Computer and information sciences CreativeWork Preprint article Article 2022 ftdatacite https://doi.org/10.48550/arxiv.2206.10721 2023-07-03T18:39:54Z We use "glide charts" (plots of sequences of root mean squared forecast errors as the target date is approached) to evaluate and compare fixed-target forecasts of Arctic sea ice. We first use them to evaluate the simple feature-engineered linear regression (FELR) forecasts of Diebold and Goebel (2021), and to compare FELR forecasts to naive pure-trend benchmark forecasts. Then we introduce a much more sophisticated feature-engineered machine learning (FEML) model, and we use glide charts to evaluate FEML forecasts and compare them to a FELR benchmark. Our substantive results include the frequent appearance of predictability thresholds, which differ across months, meaning that accuracy initially fails to improve as the target date is approached but then increases progressively once a threshold lead time is crossed. Also, we find that FEML can improve appreciably over FELR when forecasting "turning point" months in the annual cycle at horizons of one to three months ahead. ... Report Arctic Sea ice DataCite Arctic |
| spellingShingle | Econometrics econ.EM Applications stat.AP FOS Economics and business FOS Computer and information sciences Diebold, Francis X. Goebel, Maximilian Coulombe, Philippe Goulet Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... |
| title | Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... |
| title_full | Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... |
| title_fullStr | Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... |
| title_full_unstemmed | Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... |
| title_short | Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models ... |
| title_sort | assessing and comparing fixed-target forecasts of arctic sea ice: glide charts for feature-engineered linear regression and machine learning models ... |
| topic | Econometrics econ.EM Applications stat.AP FOS Economics and business FOS Computer and information sciences |
| topic_facet | Econometrics econ.EM Applications stat.AP FOS Economics and business FOS Computer and information sciences |
| url | https://dx.doi.org/10.48550/arxiv.2206.10721 https://arxiv.org/abs/2206.10721 |