Semiparametric estimation and inference of variance function with large dimensional covariates

Yanyuan Ma, Liping Zhu

Research output: Contribution to journalArticle

Abstract

We investigate the simultaneous estimation and inference of the central mean subspace and central variance subspace to reduce the effective number of covariates that predict, respectively, the mean and variability of the response variable. We study the estimation, inference and efficiency properties under different scenarios, and further propose a class of locally efficient estimators when the truly efficient estimator is not practically available. This partially explains the necessity of some dimension-reduction assumptions that are commonly imposed on the conditional mean function in estimating the central variance subspace. Comprehensive simulation studies and a data analysis are performed to demonstrate the finite sample performance and efficiency gain of the locally efficient estimators in comparison with existing estimation procedures.

Original languageEnglish (US)
Pages (from-to)567-588
Number of pages22
JournalStatistica Sinica
Volume29
Issue number2
DOIs
StatePublished - Jan 1 2019

Fingerprint

Semiparametric Inference
Semiparametric Estimation
Efficient Estimator
Variance Function
Covariates
Subspace
Simultaneous Inference
Simultaneous Estimation
Dimension Reduction
Data analysis
Simulation Study
Predict
Scenarios
Demonstrate
Semiparametric estimation
Estimator
Semiparametric inference
Inference

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{c2e9946d829447a4a034dd8246e66507,
title = "Semiparametric estimation and inference of variance function with large dimensional covariates",
abstract = "We investigate the simultaneous estimation and inference of the central mean subspace and central variance subspace to reduce the effective number of covariates that predict, respectively, the mean and variability of the response variable. We study the estimation, inference and efficiency properties under different scenarios, and further propose a class of locally efficient estimators when the truly efficient estimator is not practically available. This partially explains the necessity of some dimension-reduction assumptions that are commonly imposed on the conditional mean function in estimating the central variance subspace. Comprehensive simulation studies and a data analysis are performed to demonstrate the finite sample performance and efficiency gain of the locally efficient estimators in comparison with existing estimation procedures.",
author = "Yanyuan Ma and Liping Zhu",
year = "2019",
month = "1",
day = "1",
doi = "10.5705/ss.202017.0084",
language = "English (US)",
volume = "29",
pages = "567--588",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "2",

}

Semiparametric estimation and inference of variance function with large dimensional covariates. / Ma, Yanyuan; Zhu, Liping.

In: Statistica Sinica, Vol. 29, No. 2, 01.01.2019, p. 567-588.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Semiparametric estimation and inference of variance function with large dimensional covariates

AU - Ma, Yanyuan

AU - Zhu, Liping

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We investigate the simultaneous estimation and inference of the central mean subspace and central variance subspace to reduce the effective number of covariates that predict, respectively, the mean and variability of the response variable. We study the estimation, inference and efficiency properties under different scenarios, and further propose a class of locally efficient estimators when the truly efficient estimator is not practically available. This partially explains the necessity of some dimension-reduction assumptions that are commonly imposed on the conditional mean function in estimating the central variance subspace. Comprehensive simulation studies and a data analysis are performed to demonstrate the finite sample performance and efficiency gain of the locally efficient estimators in comparison with existing estimation procedures.

AB - We investigate the simultaneous estimation and inference of the central mean subspace and central variance subspace to reduce the effective number of covariates that predict, respectively, the mean and variability of the response variable. We study the estimation, inference and efficiency properties under different scenarios, and further propose a class of locally efficient estimators when the truly efficient estimator is not practically available. This partially explains the necessity of some dimension-reduction assumptions that are commonly imposed on the conditional mean function in estimating the central variance subspace. Comprehensive simulation studies and a data analysis are performed to demonstrate the finite sample performance and efficiency gain of the locally efficient estimators in comparison with existing estimation procedures.

UR - http://www.scopus.com/inward/record.url?scp=85072067998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072067998&partnerID=8YFLogxK

U2 - 10.5705/ss.202017.0084

DO - 10.5705/ss.202017.0084

M3 - Article

AN - SCOPUS:85072067998

VL - 29

SP - 567

EP - 588

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 2

ER -