On the existence of strongly consistent rules for estimation and classification

S. R. Kulkarni; O. Zeitouni

On the existence of strongly consistent rules for estimation and classification

Research output: Contribution to conference › Paper › peer-review

Abstract

Suppose we observe x₁, x₂, ... ε λ drawn i.i.d. according to some unknown distribution p selected from a family of distributions P. Let f:P → Λ be a parameterization of P ε P. In this paper, we study necessary and sufficient conditions for the existence of strongly consistent estimators of f(P). A number of previous results along these lines are special cases of our main result.

Original language	English (US)
Pages	255
Number of pages	1
State	Published - 1995
Event	Proceedings of the 1995 IEEE International Symposium on Information Theory - Whistler, BC, Can Duration: Sep 17 1995 → Sep 22 1995

Other

Other	Proceedings of the 1995 IEEE International Symposium on Information Theory
City	Whistler, BC, Can
Period	9/17/95 → 9/22/95

All Science Journal Classification (ASJC) codes

Theoretical Computer Science
Information Systems
Modeling and Simulation
Applied Mathematics

Cite this

@conference{7594c6b1c28644bd8dcf188cfcd86916,

title = "On the existence of strongly consistent rules for estimation and classification",

abstract = "Suppose we observe x1, x2, ... ε λ drawn i.i.d. according to some unknown distribution p selected from a family of distributions P. Let f:P → Λ be a parameterization of P ε P. In this paper, we study necessary and sufficient conditions for the existence of strongly consistent estimators of f(P). A number of previous results along these lines are special cases of our main result.",

author = "Kulkarni, {S. R.} and O. Zeitouni",

year = "1995",

language = "English (US)",

pages = "255",

note = "Proceedings of the 1995 IEEE International Symposium on Information Theory ; Conference date: 17-09-1995 Through 22-09-1995",

}

TY - CONF

T1 - On the existence of strongly consistent rules for estimation and classification

AU - Kulkarni, S. R.

AU - Zeitouni, O.

PY - 1995

Y1 - 1995

N2 - Suppose we observe x1, x2, ... ε λ drawn i.i.d. according to some unknown distribution p selected from a family of distributions P. Let f:P → Λ be a parameterization of P ε P. In this paper, we study necessary and sufficient conditions for the existence of strongly consistent estimators of f(P). A number of previous results along these lines are special cases of our main result.

AB - Suppose we observe x1, x2, ... ε λ drawn i.i.d. according to some unknown distribution p selected from a family of distributions P. Let f:P → Λ be a parameterization of P ε P. In this paper, we study necessary and sufficient conditions for the existence of strongly consistent estimators of f(P). A number of previous results along these lines are special cases of our main result.

UR - http://www.scopus.com/inward/record.url?scp=0029193450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029193450&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029193450

SP - 255

T2 - Proceedings of the 1995 IEEE International Symposium on Information Theory

Y2 - 17 September 1995 through 22 September 1995

ER -

On the existence of strongly consistent rules for estimation and classification

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this