Third-order asymptomic properties of a class of test statistics under a local alternative

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Suppose that {Xi; i = 1, 2, ...,} is a sequence of p-dimensional random vectors forming a stochastic process. Let pn, θ(Xn), Xn ∈ Rnp, be the probability density function of Xn = (X1, ..., Xn) depending on θ ∈ Θ, where Θ is an open set of R1. We consider to test a simple hypothesis H : θ = θ0 against the alternative A : θ ≠ θ0. For this testing problem we introduce a class of tests S, which contains the likelihood ratio, Wald, modified Wald, and Rao tests as special cases. Then we derive the third-order asymptotic expansion of the distribution of T ∈ S under a sequence of local alternatives. Using this result we elucidate various third-order asymptotic properties of T ∈ S (e.g., Bartlett's adjustments, third-order asymptotically most powerful properties). Our results are very general, and can be applied to the i.i.d. case, multivariate analysis, and time series analysis. Two concrete examples will be given. One is a Gaussian ARMA process (dependent case), and the other is a nonlinear regression model (non-identically distributed case).

Original languageEnglish
Pages (from-to)223-238
Number of pages16
JournalJournal of Multivariate Analysis
Volume37
Issue number2
DOIs
Publication statusPublished - 1991
Externally publishedYes

Fingerprint

Local Alternatives
Time series analysis
Random processes
Probability density function
Test Statistic
Statistics
Testing
ARMA Process
Nonlinear Regression Model
Multivariate Analysis
Time Series Analysis
Likelihood Ratio
Random Vector
Gaussian Process
Open set
Asymptotic Properties
Asymptotic Expansion
Stochastic Processes
Adjustment
Dependent

Keywords

  • asymptotic expansion
  • Bartlett's adjustment
  • Gaussian ARMA process
  • higher-order asymptotics of tests
  • local alternative
  • nonlinear regression model
  • third-order most powerful test

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Numerical Analysis
  • Statistics and Probability

Cite this

Third-order asymptomic properties of a class of test statistics under a local alternative. / Taniguchi, Masanobu.

In: Journal of Multivariate Analysis, Vol. 37, No. 2, 1991, p. 223-238.

Research output: Contribution to journalArticle

@article{136996314720437a9378f238e343626e,
title = "Third-order asymptomic properties of a class of test statistics under a local alternative",
abstract = "Suppose that {Xi; i = 1, 2, ...,} is a sequence of p-dimensional random vectors forming a stochastic process. Let pn, θ(Xn), Xn ∈ Rnp, be the probability density function of Xn = (X1, ..., Xn) depending on θ ∈ Θ, where Θ is an open set of R1. We consider to test a simple hypothesis H : θ = θ0 against the alternative A : θ ≠ θ0. For this testing problem we introduce a class of tests S, which contains the likelihood ratio, Wald, modified Wald, and Rao tests as special cases. Then we derive the third-order asymptotic expansion of the distribution of T ∈ S under a sequence of local alternatives. Using this result we elucidate various third-order asymptotic properties of T ∈ S (e.g., Bartlett's adjustments, third-order asymptotically most powerful properties). Our results are very general, and can be applied to the i.i.d. case, multivariate analysis, and time series analysis. Two concrete examples will be given. One is a Gaussian ARMA process (dependent case), and the other is a nonlinear regression model (non-identically distributed case).",
keywords = "asymptotic expansion, Bartlett's adjustment, Gaussian ARMA process, higher-order asymptotics of tests, local alternative, nonlinear regression model, third-order most powerful test",
author = "Masanobu Taniguchi",
year = "1991",
doi = "10.1016/0047-259X(91)90081-C",
language = "English",
volume = "37",
pages = "223--238",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Third-order asymptomic properties of a class of test statistics under a local alternative

AU - Taniguchi, Masanobu

PY - 1991

Y1 - 1991

N2 - Suppose that {Xi; i = 1, 2, ...,} is a sequence of p-dimensional random vectors forming a stochastic process. Let pn, θ(Xn), Xn ∈ Rnp, be the probability density function of Xn = (X1, ..., Xn) depending on θ ∈ Θ, where Θ is an open set of R1. We consider to test a simple hypothesis H : θ = θ0 against the alternative A : θ ≠ θ0. For this testing problem we introduce a class of tests S, which contains the likelihood ratio, Wald, modified Wald, and Rao tests as special cases. Then we derive the third-order asymptotic expansion of the distribution of T ∈ S under a sequence of local alternatives. Using this result we elucidate various third-order asymptotic properties of T ∈ S (e.g., Bartlett's adjustments, third-order asymptotically most powerful properties). Our results are very general, and can be applied to the i.i.d. case, multivariate analysis, and time series analysis. Two concrete examples will be given. One is a Gaussian ARMA process (dependent case), and the other is a nonlinear regression model (non-identically distributed case).

AB - Suppose that {Xi; i = 1, 2, ...,} is a sequence of p-dimensional random vectors forming a stochastic process. Let pn, θ(Xn), Xn ∈ Rnp, be the probability density function of Xn = (X1, ..., Xn) depending on θ ∈ Θ, where Θ is an open set of R1. We consider to test a simple hypothesis H : θ = θ0 against the alternative A : θ ≠ θ0. For this testing problem we introduce a class of tests S, which contains the likelihood ratio, Wald, modified Wald, and Rao tests as special cases. Then we derive the third-order asymptotic expansion of the distribution of T ∈ S under a sequence of local alternatives. Using this result we elucidate various third-order asymptotic properties of T ∈ S (e.g., Bartlett's adjustments, third-order asymptotically most powerful properties). Our results are very general, and can be applied to the i.i.d. case, multivariate analysis, and time series analysis. Two concrete examples will be given. One is a Gaussian ARMA process (dependent case), and the other is a nonlinear regression model (non-identically distributed case).

KW - asymptotic expansion

KW - Bartlett's adjustment

KW - Gaussian ARMA process

KW - higher-order asymptotics of tests

KW - local alternative

KW - nonlinear regression model

KW - third-order most powerful test

UR - http://www.scopus.com/inward/record.url?scp=0001638264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001638264&partnerID=8YFLogxK

U2 - 10.1016/0047-259X(91)90081-C

DO - 10.1016/0047-259X(91)90081-C

M3 - Article

VL - 37

SP - 223

EP - 238

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

IS - 2

ER -