Efficient Fully Distribution-Free Center-Outward Rank Tests for Multiple-Output Regression and MANOVA

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10450972" target="_blank" >RIV/00216208:11320/23:10450972 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=tyOvSTl~pM" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=tyOvSTl~pM</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1080/01621459.2021.2021921" target="_blank" >10.1080/01621459.2021.2021921</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Fully Distribution-Free Center-Outward Rank Tests for Multiple-Output Regression and MANOVA

Popis výsledku v původním jazyce

Extending rank-based inference to a multivariate setting such as multiple-output regression or MANOVA with unspecified d-dimensional error density has remained an open problem for more than half a century. None of the many solutions proposed so far is enjoying the combination of distribution-freeness and efficiency that makes rank-based inference a successful tool in the univariate setting. A concept of center-outward multivariate ranks and signs based on measure transportation ideas has been introduced recently. Center-outward ranks and signs are not only distribution-free but achieve in dimension d &gt; 1 the (essential) maximal ancillarity property of traditional univariate ranks. In the present case, we show that fully distribution-free testing procedures based on center-outward ranks can achieve parametric efficiency. We establish the Hajek representation and asymptotic normality results required in the construction of such tests in multiple-output regression and MANOVA models. Simulations and an empirical study demonstrate the excellent performance of the proposed procedures.

Název v anglickém jazyce

Efficient Fully Distribution-Free Center-Outward Rank Tests for Multiple-Output Regression and MANOVA

Popis výsledku anglicky

Extending rank-based inference to a multivariate setting such as multiple-output regression or MANOVA with unspecified d-dimensional error density has remained an open problem for more than half a century. None of the many solutions proposed so far is enjoying the combination of distribution-freeness and efficiency that makes rank-based inference a successful tool in the univariate setting. A concept of center-outward multivariate ranks and signs based on measure transportation ideas has been introduced recently. Center-outward ranks and signs are not only distribution-free but achieve in dimension d &gt; 1 the (essential) maximal ancillarity property of traditional univariate ranks. In the present case, we show that fully distribution-free testing procedures based on center-outward ranks can achieve parametric efficiency. We establish the Hajek representation and asymptotic normality results required in the construction of such tests in multiple-output regression and MANOVA models. Simulations and an empirical study demonstrate the excellent performance of the proposed procedures.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of the American Statistical Association

ISSN

0162-1459

e-ISSN

1537-274X

Svazek periodika

118

Číslo periodika v rámci svazku

543

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

17

Strana od-do

1923-1939

Kód UT WoS článku

000784656000001

EID výsledku v databázi Scopus

2-s2.0-85129555529