Buchumschlag

On testing equal conditional predictive ability under measurement error

Loss functions are widely used to compare several competing forecasts. However, forecast comparisons are often based on mismeasured proxy variables for the true target. We introduce the concept of exact robustness to measurement error for loss functions and fully characterize this class of loss func...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hoga, Yannick (VerfasserIn) , Dimitriadis, Timo (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 2023
In: Journal of business & economic statistics
Year: 2023, Jahrgang: 41, Heft: 2, Pages: 364-376
ISSN:1537-2707
DOI:10.1080/07350015.2021.2021923
Schlagworte:
Aufsatz in Zeitschrift
Online-Zugang:Verlag, kostenfrei: https://www.tandfonline.com/doi/pdf/10.1080/07350015.2021.2021923
Resolving-System, kostenfrei, Volltext: https://doi.org/10.1080/07350015.2021.2021923
Volltext
Verfasserangaben:Yannick Hoga and Timo Dimitriadis

MARC

LEADER 00000caa a2200000 c 4500
001 185405161X
003 DE-627
005 20240517114242.0
007 cr uuu---uuuuu
008 230801s2023 xx |||||o 00| ||eng c
024 7 |a 10.1080/07350015.2021.2021923  |2 doi 
035 |a (DE-627)185405161X 
035 |a (DE-599)KXP185405161X 
035 |a (OCoLC)1425213684 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 17  |2 sdnb 
100 1 |a Hoga, Yannick  |e VerfasserIn  |0 (DE-588)1297871553  |0 (DE-627)1854052381  |4 aut 
245 1 0 |a On testing equal conditional predictive ability under measurement error  |c Yannick Hoga and Timo Dimitriadis 
264 1 |c 2023 
300 |a 13 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Online veröffentlicht am 3. Februar 2022 
500 |a Gesehen am 01.08.2023 
520 |a Loss functions are widely used to compare several competing forecasts. However, forecast comparisons are often based on mismeasured proxy variables for the true target. We introduce the concept of exact robustness to measurement error for loss functions and fully characterize this class of loss functions as the Bregman class. Hence, only conditional mean forecasts can be evaluated exactly robustly. For such exactly robust loss functions, forecast loss differences are on average unaffected by the use of proxy variables and, thus, inference on conditional predictive ability can be carried out as usual. Moreover, we show that more precise proxies give predictive ability tests higher power in discriminating between competing forecasts. Simulations illustrate the different behavior of exactly robust and nonrobust loss functions. An empirical application to U.S. GDP growth rates demonstrates the nonrobustness of quantile forecasts. It also shows that it is easier to discriminate between mean forecasts issued at different horizons if a better proxy for GDP growth is used. 
650 4 |a Equal predictive ability 
650 4 |a Forecasting 
650 4 |a Hypothesis testing 
650 4 |a Measurement error 
655 4 |0 (DE-206)49  |a Aufsatz in Zeitschrift  |5 DE-206 
700 1 |a Dimitriadis, Timo  |e VerfasserIn  |0 (DE-588)1230883045  |0 (DE-627)1753224217  |4 aut 
773 0 8 |i Enthalten in  |t Journal of business & economic statistics  |d Abingdon : Taylor & Francis, 1983  |g 41(2023), 2, Seite 364-376  |h Online-Ressource  |w (DE-627)327084073  |w (DE-600)2043744-4  |w (DE-576)250711516  |x 1537-2707  |7 nnas  |a On testing equal conditional predictive ability under measurement error 
773 1 8 |g volume:41  |g year:2023  |g number:2  |g pages:364-376  |g extent:13  |a On testing equal conditional predictive ability under measurement error 
856 4 0 |u https://www.tandfonline.com/doi/pdf/10.1080/07350015.2021.2021923  |x Verlag  |z kostenfrei 
856 4 0 |u https://doi.org/10.1080/07350015.2021.2021923  |x Resolving-System  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20230801 
993 |a Article 
994 |a 2023 
998 |g 1230883045  |a Dimitriadis, Timo  |m 1230883045:Dimitriadis, Timo  |d 180000  |d 181000  |e 180000PD1230883045  |e 181000PD1230883045  |k 0/180000/  |k 1/180000/181000/  |p 2  |y j 
999 |a KXP-PPN185405161X  |e 436189924X 
BIB |a Y 
SER |a journal 
JSO |a {"person":[{"role":"aut","display":"Hoga, Yannick","roleDisplay":"VerfasserIn","given":"Yannick","family":"Hoga"},{"family":"Dimitriadis","given":"Timo","display":"Dimitriadis, Timo","roleDisplay":"VerfasserIn","role":"aut"}],"title":[{"title_sort":"On testing equal conditional predictive ability under measurement error","title":"On testing equal conditional predictive ability under measurement error"}],"note":["Online veröffentlicht am 3. Februar 2022","Gesehen am 01.08.2023"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"language":["eng"],"recId":"185405161X","name":{"displayForm":["Yannick Hoga and Timo Dimitriadis"]},"origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"2023"}],"id":{"doi":["10.1080/07350015.2021.2021923"],"eki":["185405161X"]},"physDesc":[{"extent":"13 S."}],"relHost":[{"title":[{"subtitle":"JBES ; a publication of the American Statistical Association","title":"Journal of business & economic statistics","title_sort":"Journal of business & economic statistics"}],"disp":"On testing equal conditional predictive ability under measurement errorJournal of business & economic statistics","note":["Gesehen am 28.09.22"],"type":{"media":"Online-Ressource","bibl":"periodical"},"language":["eng"],"recId":"327084073","pubHistory":["1.1983 -"],"titleAlt":[{"title":"Journal of business and economic statistics"},{"title":"JBES"}],"part":{"volume":"41","text":"41(2023), 2, Seite 364-376","extent":"13","year":"2023","pages":"364-376","issue":"2"},"origin":[{"dateIssuedKey":"1983","publisher":"Taylor & Francis ; American Statistical Association","dateIssuedDisp":"1983-","publisherPlace":"Abingdon ; Alexandria, Va."}],"id":{"issn":["1537-2707"],"eki":["327084073"],"zdb":["2043744-4"]},"physDesc":[{"extent":"Online-Ressource"}]}]} 
SRT |a HOGAYANNICONTESTINGE2023 

Ähnliche Einträge