Empirical process of residuals for high-dimensional linear models

We give a stochastic expansion for the empirical distribution function F^nF^n\hat{F}_n of residuals in a p-dimensional linear model. This expansion holds for p increasing with n. It shows that, for high-dimensional linear models, F^nF^n\hat{F}_n strongly depends on the chosen estimator θ^θ^\hat{\the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Mammen, Enno (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 1996
In: The annals of statistics
Year: 1996, Jahrgang: 24, Heft: 1, Pages: 307-335$19
ISSN:2168-8966
DOI:10.1214/aos/1033066211
Online-Zugang:Verlag, Volltext: http://dx.doi.org/10.1214/aos/1033066211
Verlag, Volltext: https://projecteuclid.org/euclid.aos/1033066211
Verlag, Volltext: https://projecteuclid.org/download/pdf_1/euclid.aos/1033066211
Volltext
Verfasserangaben:Enno Mammen

MARC

LEADER 00000caa a2200000 c 4500
001 1570095302
003 DE-627
005 20220814081137.0
007 cr uuu---uuuuu
008 180222s1996 xx |||||o 00| ||eng c
024 7 |a 10.1214/aos/1033066211  |2 doi 
035 |a (DE-627)1570095302 
035 |a (DE-576)500095302 
035 |a (DE-599)BSZ500095302 
035 |a (OCoLC)1340992036 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 27  |2 sdnb 
100 1 |a Mammen, Enno  |d 1955-  |e VerfasserIn  |0 (DE-588)170668606  |0 (DE-627)060788658  |0 (DE-576)13153159X  |4 aut 
245 1 0 |a Empirical process of residuals for high-dimensional linear models  |c Enno Mammen 
264 1 |c 1996 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a First available in Project Euclid: 26 September 2002 
500 |a Gesehen am 22.02.2018 
520 |a We give a stochastic expansion for the empirical distribution function F^nF^n\hat{F}_n of residuals in a p-dimensional linear model. This expansion holds for p increasing with n. It shows that, for high-dimensional linear models, F^nF^n\hat{F}_n strongly depends on the chosen estimator θ^θ^\hat{\theta} of the parameter θθ\theta of the linear model. In particular, if one uses an ML-estimator θ^MLθ^ML\hat{\theta}_{ML} which is ML motivated by a wrongly specified error distribution function G, then F^nF^n\hat{F}_n is biased toward G. For p^2 / n \to \infty$, this bias effect is of larger order than the stochastic fluctuations of the empirical process. Hence, the statistical analysis may just reproduce the assumptions imposed. 
650 4 |a asymptotics with increasing dimension 
650 4 |a Empirical processes 
650 4 |a linear models 
650 4 |a residuals 
773 0 8 |i Enthalten in  |t The annals of statistics  |d Hayward, Calif. : IMS Business Off., 1973  |g 24(1996), 1, Seite 307-335$19  |h Online-Ressource  |w (DE-627)270129162  |w (DE-600)1476670-X  |w (DE-576)094425213  |x 2168-8966  |7 nnas  |a Empirical process of residuals for high-dimensional linear models 
773 1 8 |g volume:24  |g year:1996  |g number:1  |g pages:307-335$19  |a Empirical process of residuals for high-dimensional linear models 
856 4 0 |u http://dx.doi.org/10.1214/aos/1033066211  |x Verlag  |x Resolving-System  |3 Volltext 
856 4 0 |u https://projecteuclid.org/euclid.aos/1033066211  |x Verlag  |3 Volltext 
856 4 0 |u https://projecteuclid.org/download/pdf_1/euclid.aos/1033066211  |x Verlag  |3 Volltext 
951 |a AR 
992 |a 20180222 
993 |a Article 
994 |a 1996 
998 |g 170668606  |a Mammen, Enno  |m 170668606:Mammen, Enno  |d 110000  |d 110200  |d 110000  |d 110400  |e 110000PM170668606  |e 110200PM170668606  |e 110000PM170668606  |e 110400PM170668606  |k 0/110000/  |k 1/110000/110200/  |k 0/110000/  |k 1/110000/110400/  |p 1  |x j  |y j 
999 |a KXP-PPN1570095302  |e 3000348751 
BIB |a Y 
SER |a journal 
JSO |a {"person":[{"display":"Mammen, Enno","family":"Mammen","given":"Enno","role":"aut"}],"name":{"displayForm":["Enno Mammen"]},"title":[{"title":"Empirical process of residuals for high-dimensional linear models","title_sort":"Empirical process of residuals for high-dimensional linear models"}],"relHost":[{"part":{"pages":"307-335$19","text":"24(1996), 1, Seite 307-335$19","volume":"24","year":"1996","issue":"1"},"disp":"Empirical process of residuals for high-dimensional linear modelsThe annals of statistics","corporate":[{"role":"isb","display":"Institute of Mathematical Statistics"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"annals of statistics","title":"The annals of statistics","subtitle":"an official journal of the Institute of Mathematical Statistics"}],"id":{"zdb":["1476670-X"],"eki":["270129162"],"issn":["2168-8966"]},"origin":[{"dateIssuedKey":"1973","dateIssuedDisp":"1973-","publisher":"IMS Business Off.","publisherPlace":"Hayward, Calif."}],"note":["Gesehen am 08-06-21"],"language":["eng"],"recId":"270129162","pubHistory":["1.1973 - 23.1995; 24.1996 -"]}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"id":{"eki":["1570095302"],"doi":["10.1214/aos/1033066211"]},"origin":[{"dateIssuedDisp":"1996","dateIssuedKey":"1996"}],"language":["eng"],"recId":"1570095302","note":["First available in Project Euclid: 26 September 2002","Gesehen am 22.02.2018"]} 
SRT |a MAMMENENNOEMPIRICALP1996