Ranking and selection with covariates

Haihui Shen; L. Jeff Hong; Xiaowei Zhang

doi:10.1109/WSC.2017.8247946

Ranking and selection with covariates

Haihui Shen, L. Jeff Hong, Xiaowei Zhang

Department of Economics and Finance

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

11 Citations (Scopus)

Abstract

We consider a new ranking and selection problem in which the performance of each alternative depends on some observable random covariates. The best alternative is thus not constant but depends on the values of the covariates. Assuming a linear model that relates the mean performance of an alternative and the covariates, we design selection procedures producing policies that represent the best alternative as a function in the covariates. We prove that the selection procedures can provide certain statistical guarantee, which is defined via a nontrivial generalization of the concept of probability of correct selection that is widely used in the conventional ranking and selection setting.

Original language	English
Title of host publication	2017 Winter Simulation Conference (WSC)
Publisher	IEEE
Pages	2137-2148
ISBN (Electronic)	9781538634288
DOIs	https://doi.org/10.1109/WSC.2017.8247946
Publication status	Published - Dec 2017
Event	2017 Winter Simulation Conference, WSC 2017 - Las Vegas, United States Duration: 3 Dec 2017 → 6 Dec 2017 http://meetings2.informs.org/wordpress/wsc2017/

Publication series

Name	Simulation Winter Conference
Publisher	IEEE
ISSN (Print)	0891-7736
ISSN (Electronic)	1558-4305

Conference

Conference	2017 Winter Simulation Conference, WSC 2017
Abbreviated title	WSC 2017
Place	United States
City	Las Vegas
Period	3/12/17 → 6/12/17
Internet address	http://meetings2.informs.org/wordpress/wsc2017/

Access Output

10.1109/WSC.2017.8247946

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{187b797f0d1b403fb49adb38f9aa1796,

title = "Ranking and selection with covariates",

abstract = "We consider a new ranking and selection problem in which the performance of each alternative depends on some observable random covariates. The best alternative is thus not constant but depends on the values of the covariates. Assuming a linear model that relates the mean performance of an alternative and the covariates, we design selection procedures producing policies that represent the best alternative as a function in the covariates. We prove that the selection procedures can provide certain statistical guarantee, which is defined via a nontrivial generalization of the concept of probability of correct selection that is widely used in the conventional ranking and selection setting.",

author = "Haihui Shen and Hong, {L. Jeff} and Xiaowei Zhang",

year = "2017",

month = dec,

doi = "10.1109/WSC.2017.8247946",

language = "English",

series = "Simulation Winter Conference",

publisher = "IEEE",

pages = "2137--2148",

booktitle = "2017 Winter Simulation Conference (WSC)",

address = "United States",

note = "2017 Winter Simulation Conference, WSC 2017, WSC 2017 ; Conference date: 03-12-2017 Through 06-12-2017",

url = "http://meetings2.informs.org/wordpress/wsc2017/",

}

TY - GEN

T1 - Ranking and selection with covariates

AU - Shen, Haihui

AU - Hong, L. Jeff

AU - Zhang, Xiaowei

PY - 2017/12

Y1 - 2017/12

N2 - We consider a new ranking and selection problem in which the performance of each alternative depends on some observable random covariates. The best alternative is thus not constant but depends on the values of the covariates. Assuming a linear model that relates the mean performance of an alternative and the covariates, we design selection procedures producing policies that represent the best alternative as a function in the covariates. We prove that the selection procedures can provide certain statistical guarantee, which is defined via a nontrivial generalization of the concept of probability of correct selection that is widely used in the conventional ranking and selection setting.

AB - We consider a new ranking and selection problem in which the performance of each alternative depends on some observable random covariates. The best alternative is thus not constant but depends on the values of the covariates. Assuming a linear model that relates the mean performance of an alternative and the covariates, we design selection procedures producing policies that represent the best alternative as a function in the covariates. We prove that the selection procedures can provide certain statistical guarantee, which is defined via a nontrivial generalization of the concept of probability of correct selection that is widely used in the conventional ranking and selection setting.

UR - http://www.scopus.com/inward/record.url?scp=85044541872&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85044541872&origin=recordpage

U2 - 10.1109/WSC.2017.8247946

DO - 10.1109/WSC.2017.8247946

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Simulation Winter Conference

SP - 2137

EP - 2148

BT - 2017 Winter Simulation Conference (WSC)

PB - IEEE

T2 - 2017 Winter Simulation Conference, WSC 2017

Y2 - 3 December 2017 through 6 December 2017

ER -

Ranking and selection with covariates

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Combining Stylized Models and Simulation Models for Metamodeling and Simulation Optimization with Applications in Queueing Systems

Cite this

Ranking and selection with covariates

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Combining Stylized Models and Simulation Models for Metamodeling and Simulation Optimization with Applications in Queueing Systems

Cite this