Saddlepoint test in measurement error models

Yanyuan Ma, Elvezio Ronchetti

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

We develop second-order hypothesis testing procedures in functional measurement error models for small or moderate sample sizes, where the classical first-order asymptotic analysis often fails to provide accurate results. In functional models no distributional assumptions are made on the unobservable covariates and this leads to semiparametric models. Our testing procedure is derived using saddlepoint techniques and is based on an empirical distribution estimation subject to the null hypothesis constraints, in combination with a set of estimating equations which avoid a distribution approximation. The validity of the method is proved in theorems for both simple and composite hypothesis tests, and is demonstrated through simulation and a farm size data analysis.

Original languageEnglish (US)
Pages (from-to)147-156
Number of pages10
JournalJournal of the American Statistical Association
Volume106
Issue number493
DOIs
StatePublished - Mar 1 2011

Fingerprint

Measurement Error Model
Saddlepoint
Composite Hypothesis
Functional Model
Empirical Distribution
Estimating Equation
Semiparametric Model
Hypothesis Test
Hypothesis Testing
Null hypothesis
Asymptotic Analysis
Covariates
Data analysis
Sample Size
First-order
Testing
Approximation
Theorem
Simulation
Measurement error

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Ma, Yanyuan ; Ronchetti, Elvezio. / Saddlepoint test in measurement error models. In: Journal of the American Statistical Association. 2011 ; Vol. 106, No. 493. pp. 147-156.
@article{42ab5038797e45cbafa631bd28a4f0fd,
title = "Saddlepoint test in measurement error models",
abstract = "We develop second-order hypothesis testing procedures in functional measurement error models for small or moderate sample sizes, where the classical first-order asymptotic analysis often fails to provide accurate results. In functional models no distributional assumptions are made on the unobservable covariates and this leads to semiparametric models. Our testing procedure is derived using saddlepoint techniques and is based on an empirical distribution estimation subject to the null hypothesis constraints, in combination with a set of estimating equations which avoid a distribution approximation. The validity of the method is proved in theorems for both simple and composite hypothesis tests, and is demonstrated through simulation and a farm size data analysis.",
author = "Yanyuan Ma and Elvezio Ronchetti",
year = "2011",
month = "3",
day = "1",
doi = "10.1198/jasa.2011.tm10031",
language = "English (US)",
volume = "106",
pages = "147--156",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "493",

}

Saddlepoint test in measurement error models. / Ma, Yanyuan; Ronchetti, Elvezio.

In: Journal of the American Statistical Association, Vol. 106, No. 493, 01.03.2011, p. 147-156.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Saddlepoint test in measurement error models

AU - Ma, Yanyuan

AU - Ronchetti, Elvezio

PY - 2011/3/1

Y1 - 2011/3/1

N2 - We develop second-order hypothesis testing procedures in functional measurement error models for small or moderate sample sizes, where the classical first-order asymptotic analysis often fails to provide accurate results. In functional models no distributional assumptions are made on the unobservable covariates and this leads to semiparametric models. Our testing procedure is derived using saddlepoint techniques and is based on an empirical distribution estimation subject to the null hypothesis constraints, in combination with a set of estimating equations which avoid a distribution approximation. The validity of the method is proved in theorems for both simple and composite hypothesis tests, and is demonstrated through simulation and a farm size data analysis.

AB - We develop second-order hypothesis testing procedures in functional measurement error models for small or moderate sample sizes, where the classical first-order asymptotic analysis often fails to provide accurate results. In functional models no distributional assumptions are made on the unobservable covariates and this leads to semiparametric models. Our testing procedure is derived using saddlepoint techniques and is based on an empirical distribution estimation subject to the null hypothesis constraints, in combination with a set of estimating equations which avoid a distribution approximation. The validity of the method is proved in theorems for both simple and composite hypothesis tests, and is demonstrated through simulation and a farm size data analysis.

UR - http://www.scopus.com/inward/record.url?scp=79954561686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954561686&partnerID=8YFLogxK

U2 - 10.1198/jasa.2011.tm10031

DO - 10.1198/jasa.2011.tm10031

M3 - Article

AN - SCOPUS:79954561686

VL - 106

SP - 147

EP - 156

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 493

ER -