Large deviation asymptotics for statistical treatment rules

Taisuke Otsu

doi:10.1016/j.econlet.2008.04.009

Large deviation asymptotics for statistical treatment rules

Research output: Contribution to journal › Article › peer-review

Abstract

This note applies large deviation-based optimality theory to evaluate treatment rules for treatment assignment problems. We find nearly optimal treatment rules whose asymptotic maximum large deviation risks can be arbitrary close to the corresponding minimax bounds.

Original language	English
Pages (from-to)	53-56
Number of pages	4
Journal	Economics Letters
Volume	101
Issue number	1
DOIs	https://doi.org/10.1016/j.econlet.2008.04.009
Publication status	Published - 2008 Oct
Externally published	Yes

Keywords

Large deviation
Treatment rule

ASJC Scopus subject areas

Finance
Economics and Econometrics

Access to Document

10.1016/j.econlet.2008.04.009

Cite this

@article{c3ac769202be45f48ecc3dd2b1dd1d8c,

title = "Large deviation asymptotics for statistical treatment rules",

abstract = "This note applies large deviation-based optimality theory to evaluate treatment rules for treatment assignment problems. We find nearly optimal treatment rules whose asymptotic maximum large deviation risks can be arbitrary close to the corresponding minimax bounds.",

keywords = "Large deviation, Treatment rule",

author = "Taisuke Otsu",

year = "2008",

month = oct,

doi = "10.1016/j.econlet.2008.04.009",

language = "English",

volume = "101",

pages = "53--56",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Large deviation asymptotics for statistical treatment rules

AU - Otsu, Taisuke

PY - 2008/10

Y1 - 2008/10

N2 - This note applies large deviation-based optimality theory to evaluate treatment rules for treatment assignment problems. We find nearly optimal treatment rules whose asymptotic maximum large deviation risks can be arbitrary close to the corresponding minimax bounds.

AB - This note applies large deviation-based optimality theory to evaluate treatment rules for treatment assignment problems. We find nearly optimal treatment rules whose asymptotic maximum large deviation risks can be arbitrary close to the corresponding minimax bounds.

KW - Large deviation

KW - Treatment rule

UR - http://www.scopus.com/inward/record.url?scp=49949114725&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49949114725&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2008.04.009

DO - 10.1016/j.econlet.2008.04.009

M3 - Article

AN - SCOPUS:49949114725

SN - 0165-1765

VL - 101

SP - 53

EP - 56

JO - Economics Letters

JF - Economics Letters

IS - 1

ER -

Large deviation asymptotics for statistical treatment rules

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this