Eintrag weiter verarbeiten
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean?
Gespeichert in:
Zeitschriftentitel: | Studies in Nonlinear Dynamics & Econometrics |
---|---|
Personen und Körperschaften: | |
In: | Studies in Nonlinear Dynamics & Econometrics, 18, 2014, 3 |
Format: | E-Article |
Sprache: | Unbestimmt |
veröffentlicht: |
Walter de Gruyter GmbH
|
Schlagwörter: |
author_facet |
Kristensen, Johannes Tang Kristensen, Johannes Tang |
---|---|
author |
Kristensen, Johannes Tang |
spellingShingle |
Kristensen, Johannes Tang Studies in Nonlinear Dynamics & Econometrics Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? Economics and Econometrics Social Sciences (miscellaneous) Analysis Economics and Econometrics Social Sciences (miscellaneous) Analysis |
author_sort |
kristensen, johannes tang |
spelling |
Kristensen, Johannes Tang 1558-3708 1081-1826 Walter de Gruyter GmbH Economics and Econometrics Social Sciences (miscellaneous) Analysis Economics and Econometrics Social Sciences (miscellaneous) Analysis http://dx.doi.org/10.1515/snde-2012-0049 <jats:title>Abstract</jats:title><jats:p>Macroeconomic forecasting using factor models estimated by principal components has become a popular research topic with many both theoretical and applied contributions in the literature. In this paper we attempt to address an often neglected issue in these models: The problem of outliers in the data. Most papers take an ad-hoc approach to this problem and simply screen datasets prior to estimation and remove anomalous observations. We investigate whether forecasting performance can be improved by using the original unscreened dataset and replacing principal components with a robust alternative. We propose to use an estimator based on least absolute deviations (LAD) as this alternative and establish a tractable method for computing the estimator. In addition to this we demonstrate the robustness features of the estimator through a number of Monte Carlo simulation studies. Finally, we apply the estimator in a simulated real-time forecasting exercise to test its merits. We use a newly compiled dataset of US macroeconomic series spanning the period 1971:2–2012:10. Our findings suggest that the chosen treatment of outliers does affect forecasting performance and that in many cases improvements can be made using a robust estimator such as the proposed LAD estimator.</jats:p> Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? Studies in Nonlinear Dynamics & Econometrics |
doi_str_mv |
10.1515/snde-2012-0049 |
facet_avail |
Online |
finc_class_facet |
Allgemeines Mathematik Wirtschaftswissenschaften |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTUxNS9zbmRlLTIwMTItMDA0OQ |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTUxNS9zbmRlLTIwMTItMDA0OQ |
institution |
DE-Pl11 DE-Rs1 DE-14 DE-105 DE-Ch1 DE-L229 DE-D275 DE-Bn3 DE-Brt1 DE-D161 DE-Zi4 DE-Gla1 DE-15 |
imprint |
Walter de Gruyter GmbH, 2014 |
imprint_str_mv |
Walter de Gruyter GmbH, 2014 |
issn |
1558-3708 1081-1826 |
issn_str_mv |
1558-3708 1081-1826 |
language |
Undetermined |
mega_collection |
Walter de Gruyter GmbH (CrossRef) |
match_str |
kristensen2014factorbasedforecastinginthepresenceofoutliersarefactorsbetterselectedandestimatedbythemedianthanbythemean |
publishDateSort |
2014 |
publisher |
Walter de Gruyter GmbH |
recordtype |
ai |
record_format |
ai |
series |
Studies in Nonlinear Dynamics & Econometrics |
source_id |
49 |
title |
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_unstemmed |
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_full |
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_fullStr |
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_full_unstemmed |
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_short |
Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_sort |
factor-based forecasting in the presence of outliers: are factors better selected and estimated by the median than by the mean? |
topic |
Economics and Econometrics Social Sciences (miscellaneous) Analysis Economics and Econometrics Social Sciences (miscellaneous) Analysis |
url |
http://dx.doi.org/10.1515/snde-2012-0049 |
publishDate |
2014 |
physical |
|
description |
<jats:title>Abstract</jats:title><jats:p>Macroeconomic forecasting using factor models estimated by principal components has become a popular research topic with many both theoretical and applied contributions in the literature. In this paper we attempt to address an often neglected issue in these models: The problem of outliers in the data. Most papers take an ad-hoc approach to this problem and simply screen datasets prior to estimation and remove anomalous observations. We investigate whether forecasting performance can be improved by using the original unscreened dataset and replacing principal components with a robust alternative. We propose to use an estimator based on least absolute deviations (LAD) as this alternative and establish a tractable method for computing the estimator. In addition to this we demonstrate the robustness features of the estimator through a number of Monte Carlo simulation studies. Finally, we apply the estimator in a simulated real-time forecasting exercise to test its merits. We use a newly compiled dataset of US macroeconomic series spanning the period 1971:2–2012:10. Our findings suggest that the chosen treatment of outliers does affect forecasting performance and that in many cases improvements can be made using a robust estimator such as the proposed LAD estimator.</jats:p> |
container_issue |
3 |
container_start_page |
0 |
container_title |
Studies in Nonlinear Dynamics & Econometrics |
container_volume |
18 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792329848971067399 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T13:15:43.08Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Factor-based+forecasting+in+the+presence+of+outliers%3A+Are+factors+better+selected+and+estimated+by+the+median+than+by+the+mean%3F&rft.date=2014-01-01&genre=article&issn=1081-1826&volume=18&issue=3&jtitle=Studies+in+Nonlinear+Dynamics+%26+Econometrics&atitle=Factor-based+forecasting+in+the+presence+of+outliers%3A+Are+factors+better+selected+and+estimated+by+the+median+than+by+the+mean%3F&aulast=Kristensen&aufirst=Johannes+Tang&rft_id=info%3Adoi%2F10.1515%2Fsnde-2012-0049&rft.language%5B0%5D=und |
SOLR | |
_version_ | 1792329848971067399 |
author | Kristensen, Johannes Tang |
author_facet | Kristensen, Johannes Tang, Kristensen, Johannes Tang |
author_sort | kristensen, johannes tang |
container_issue | 3 |
container_start_page | 0 |
container_title | Studies in Nonlinear Dynamics & Econometrics |
container_volume | 18 |
description | <jats:title>Abstract</jats:title><jats:p>Macroeconomic forecasting using factor models estimated by principal components has become a popular research topic with many both theoretical and applied contributions in the literature. In this paper we attempt to address an often neglected issue in these models: The problem of outliers in the data. Most papers take an ad-hoc approach to this problem and simply screen datasets prior to estimation and remove anomalous observations. We investigate whether forecasting performance can be improved by using the original unscreened dataset and replacing principal components with a robust alternative. We propose to use an estimator based on least absolute deviations (LAD) as this alternative and establish a tractable method for computing the estimator. In addition to this we demonstrate the robustness features of the estimator through a number of Monte Carlo simulation studies. Finally, we apply the estimator in a simulated real-time forecasting exercise to test its merits. We use a newly compiled dataset of US macroeconomic series spanning the period 1971:2–2012:10. Our findings suggest that the chosen treatment of outliers does affect forecasting performance and that in many cases improvements can be made using a robust estimator such as the proposed LAD estimator.</jats:p> |
doi_str_mv | 10.1515/snde-2012-0049 |
facet_avail | Online |
finc_class_facet | Allgemeines, Mathematik, Wirtschaftswissenschaften |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTUxNS9zbmRlLTIwMTItMDA0OQ |
imprint | Walter de Gruyter GmbH, 2014 |
imprint_str_mv | Walter de Gruyter GmbH, 2014 |
institution | DE-Pl11, DE-Rs1, DE-14, DE-105, DE-Ch1, DE-L229, DE-D275, DE-Bn3, DE-Brt1, DE-D161, DE-Zi4, DE-Gla1, DE-15 |
issn | 1558-3708, 1081-1826 |
issn_str_mv | 1558-3708, 1081-1826 |
language | Undetermined |
last_indexed | 2024-03-01T13:15:43.08Z |
match_str | kristensen2014factorbasedforecastinginthepresenceofoutliersarefactorsbetterselectedandestimatedbythemedianthanbythemean |
mega_collection | Walter de Gruyter GmbH (CrossRef) |
physical | |
publishDate | 2014 |
publishDateSort | 2014 |
publisher | Walter de Gruyter GmbH |
record_format | ai |
recordtype | ai |
series | Studies in Nonlinear Dynamics & Econometrics |
source_id | 49 |
spelling | Kristensen, Johannes Tang 1558-3708 1081-1826 Walter de Gruyter GmbH Economics and Econometrics Social Sciences (miscellaneous) Analysis Economics and Econometrics Social Sciences (miscellaneous) Analysis http://dx.doi.org/10.1515/snde-2012-0049 <jats:title>Abstract</jats:title><jats:p>Macroeconomic forecasting using factor models estimated by principal components has become a popular research topic with many both theoretical and applied contributions in the literature. In this paper we attempt to address an often neglected issue in these models: The problem of outliers in the data. Most papers take an ad-hoc approach to this problem and simply screen datasets prior to estimation and remove anomalous observations. We investigate whether forecasting performance can be improved by using the original unscreened dataset and replacing principal components with a robust alternative. We propose to use an estimator based on least absolute deviations (LAD) as this alternative and establish a tractable method for computing the estimator. In addition to this we demonstrate the robustness features of the estimator through a number of Monte Carlo simulation studies. Finally, we apply the estimator in a simulated real-time forecasting exercise to test its merits. We use a newly compiled dataset of US macroeconomic series spanning the period 1971:2–2012:10. Our findings suggest that the chosen treatment of outliers does affect forecasting performance and that in many cases improvements can be made using a robust estimator such as the proposed LAD estimator.</jats:p> Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? Studies in Nonlinear Dynamics & Econometrics |
spellingShingle | Kristensen, Johannes Tang, Studies in Nonlinear Dynamics & Econometrics, Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean?, Economics and Econometrics, Social Sciences (miscellaneous), Analysis, Economics and Econometrics, Social Sciences (miscellaneous), Analysis |
title | Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_full | Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_fullStr | Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_full_unstemmed | Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_short | Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
title_sort | factor-based forecasting in the presence of outliers: are factors better selected and estimated by the median than by the mean? |
title_unstemmed | Factor-based forecasting in the presence of outliers: Are factors better selected and estimated by the median than by the mean? |
topic | Economics and Econometrics, Social Sciences (miscellaneous), Analysis, Economics and Econometrics, Social Sciences (miscellaneous), Analysis |
url | http://dx.doi.org/10.1515/snde-2012-0049 |