Minimum distance tests and estimates based on ranks

J 2020

Minimum distance tests and estimates based on ranks

NAVRÁTIL, Radim

Základní údaje

Originální název

Minimum distance tests and estimates based on ranks

Autoři

NAVRÁTIL, Radim (203 Česká republika, garant, domácí)

Vydání

REVSTAT Statistical Journal, Lisabon, Statistics Portugal, 2020, 1645-6726

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10103 Statistics and probability

Stát vydavatele

Portugalsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 1.250

Kód RIV

RIV/00216224:14310/20:00117545

Organizační jednotka

Přírodovědecká fakulta

UT WoS

000557809200004

Klíčová slova anglicky

minimum distance estimates; ranks; robustness; tests.

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 4. 1. 2021 21:34, RNDr. Radim Navrátil, Ph.D.

Anotace

V originále

It is well known that the least squares estimate in classical linear regression model is very sensitive to violation of the assumptions, in particular normality of model errors. That is why a lot of alternative estimates has been developed to overcome these shortcomings. Quite interesting class of such estimates is formed by R-estimates. They use only ranks of response variable instead of their actual value. The goal of this paper is to extend this class by another estimates and tests based only on ranks. First, we will introduce a new rank test in linear regression model. The test statistic is based on a certain minimum distance estimator, but unlike classical rank tests in regression it is not a simple linear rank statistic. Then, we will return back to estimates and generalize minimum distance estimates for various type of distances. We will show that in some situation these tests and estimates have greater power than the classical ones. Theoretical results will be accompanied by a simulation study to illustrate finite sample behavior of estimates and tests.

Návaznosti

MUNI/A/1204/2017, interní kód MU

Název: Matematické statistické modelování 2 (Akronym: MaStaMo2)

Investor: Masarykova univerzita, Matematické statistické modelování 2, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Citovat

NAVRÁTIL, Radim. Minimum distance tests and estimates based on ranks. REVSTAT Statistical Journal. Lisabon: Statistics Portugal, 2020, roč. 18, č. 3, s. 299-310. ISSN 1645-6726.

@article{1718679,
   author = {Navrátil, Radim},
   article_location = {Lisabon},
   article_number = {3},
   keywords = {minimum distance estimates; ranks; robustness; tests.},
   language = {eng},
   issn = {1645-6726},
   journal = {REVSTAT Statistical Journal},
   title = {Minimum distance tests and estimates based on ranks},
   url = {https://www.ine.pt/revstat/pdf/REVSTAT_v18-n3-4.pdf},
   volume = {18},
   year = {2020}
}

TY  - JOUR
ID  - 1718679
AU  - Navrátil, Radim
PY  - 2020
TI  - Minimum distance tests and estimates based on ranks
JF  - REVSTAT Statistical Journal
VL  - 18
IS  - 3
SP  - 299-310
EP  - 299-310
PB  - Statistics Portugal
SN  - 16456726
KW  - minimum distance estimates
KW  - ranks
KW  - robustness
KW  - tests.
UR  - https://www.ine.pt/revstat/pdf/REVSTAT_v18-n3-4.pdf
L2  - https://www.ine.pt/revstat/pdf/REVSTAT_v18-n3-4.pdf
N2  - It is well known that the least squares estimate in classical linear regression model is very sensitive to violation of the assumptions, in particular normality of model errors. That is why a lot of alternative estimates has been developed to overcome these shortcomings. Quite interesting class of such estimates is formed by R-estimates. They use only ranks of response variable instead of their actual value. The goal of this paper is to extend this class by another estimates and tests based only on ranks. First, we will introduce a new rank test in linear regression model. The test statistic is based on a certain minimum distance estimator, but unlike classical rank tests in regression it is not a simple linear rank statistic. Then, we will return back to estimates and generalize minimum distance estimates for various type of distances. We will show that in some situation these tests and estimates have greater power than the classical ones. Theoretical results will be accompanied by a simulation study to illustrate finite sample behavior of estimates and tests.
ER  -

NAVRÁTIL, Radim. Minimum distance tests and estimates based on ranks. \textit{REVSTAT Statistical Journal}. Lisabon: Statistics Portugal, 2020, roč.~18, č.~3, s.~299-310. ISSN~1645-6726.

Podrobný výpis o publikaci