Large-sample estimation and inference in multivariate single-index models

Jingwei Wu, Hanxiang Peng, Wanzhu Tu

Research output: Contribution to journalArticle

Abstract

By optimizing index functions against different outcomes, we propose a multivariate single-index model (SIM) for development of medical indices that simultaneously work with multiple outcomes. Fitting of a multivariate SIM is not fundamentally different from fitting a univariate SIM, as the former can be written as a sum of multiple univariate SIMs with appropriate indicator functions. What have not been carefully studied are the theoretical properties of the parameter estimators. Because of the lack of asymptotic results, no formal inference procedure has been made available for multivariate SIMs. In this paper, we examine the asymptotic properties of the multivariate SIM parameter estimators. We show that, under mild regularity conditions, estimators for the multivariate SIM parameters are indeed n-consistent and asymptotically normal. We conduct a simulation study to investigate the finite-sample performance of the corresponding estimation and inference procedures. To illustrate its use in practice, we construct an index measure of urine electrolyte markers for assessing the risk of hypertension in individual subjects.

Original languageEnglish (US)
Pages (from-to)382-396
Number of pages15
JournalJournal of Multivariate Analysis
Volume171
DOIs
StatePublished - May 1 2019

Fingerprint

Single-index Model
Multivariate Models
Estimator
Univariate
Multiple Outcomes
Indicator function
Hypertension
Electrolyte
Regularity Conditions
Asymptotic Properties
Electrolytes
Index model
Inference
Simulation Study

Keywords

  • Asymptotic normality
  • Consistency
  • Mixed effect model
  • Multivariate outcomes
  • P-splines
  • Single-index models

ASJC Scopus subject areas

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

Cite this

Large-sample estimation and inference in multivariate single-index models. / Wu, Jingwei; Peng, Hanxiang; Tu, Wanzhu.

In: Journal of Multivariate Analysis, Vol. 171, 01.05.2019, p. 382-396.

Research output: Contribution to journalArticle

@article{6e7fb9efe68f4d6fa7871284acbf435b,
title = "Large-sample estimation and inference in multivariate single-index models",
abstract = "By optimizing index functions against different outcomes, we propose a multivariate single-index model (SIM) for development of medical indices that simultaneously work with multiple outcomes. Fitting of a multivariate SIM is not fundamentally different from fitting a univariate SIM, as the former can be written as a sum of multiple univariate SIMs with appropriate indicator functions. What have not been carefully studied are the theoretical properties of the parameter estimators. Because of the lack of asymptotic results, no formal inference procedure has been made available for multivariate SIMs. In this paper, we examine the asymptotic properties of the multivariate SIM parameter estimators. We show that, under mild regularity conditions, estimators for the multivariate SIM parameters are indeed n-consistent and asymptotically normal. We conduct a simulation study to investigate the finite-sample performance of the corresponding estimation and inference procedures. To illustrate its use in practice, we construct an index measure of urine electrolyte markers for assessing the risk of hypertension in individual subjects.",
keywords = "Asymptotic normality, Consistency, Mixed effect model, Multivariate outcomes, P-splines, Single-index models",
author = "Jingwei Wu and Hanxiang Peng and Wanzhu Tu",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.jmva.2019.01.003",
language = "English (US)",
volume = "171",
pages = "382--396",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Large-sample estimation and inference in multivariate single-index models

AU - Wu, Jingwei

AU - Peng, Hanxiang

AU - Tu, Wanzhu

PY - 2019/5/1

Y1 - 2019/5/1

N2 - By optimizing index functions against different outcomes, we propose a multivariate single-index model (SIM) for development of medical indices that simultaneously work with multiple outcomes. Fitting of a multivariate SIM is not fundamentally different from fitting a univariate SIM, as the former can be written as a sum of multiple univariate SIMs with appropriate indicator functions. What have not been carefully studied are the theoretical properties of the parameter estimators. Because of the lack of asymptotic results, no formal inference procedure has been made available for multivariate SIMs. In this paper, we examine the asymptotic properties of the multivariate SIM parameter estimators. We show that, under mild regularity conditions, estimators for the multivariate SIM parameters are indeed n-consistent and asymptotically normal. We conduct a simulation study to investigate the finite-sample performance of the corresponding estimation and inference procedures. To illustrate its use in practice, we construct an index measure of urine electrolyte markers for assessing the risk of hypertension in individual subjects.

AB - By optimizing index functions against different outcomes, we propose a multivariate single-index model (SIM) for development of medical indices that simultaneously work with multiple outcomes. Fitting of a multivariate SIM is not fundamentally different from fitting a univariate SIM, as the former can be written as a sum of multiple univariate SIMs with appropriate indicator functions. What have not been carefully studied are the theoretical properties of the parameter estimators. Because of the lack of asymptotic results, no formal inference procedure has been made available for multivariate SIMs. In this paper, we examine the asymptotic properties of the multivariate SIM parameter estimators. We show that, under mild regularity conditions, estimators for the multivariate SIM parameters are indeed n-consistent and asymptotically normal. We conduct a simulation study to investigate the finite-sample performance of the corresponding estimation and inference procedures. To illustrate its use in practice, we construct an index measure of urine electrolyte markers for assessing the risk of hypertension in individual subjects.

KW - Asymptotic normality

KW - Consistency

KW - Mixed effect model

KW - Multivariate outcomes

KW - P-splines

KW - Single-index models

UR - http://www.scopus.com/inward/record.url?scp=85061087363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061087363&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2019.01.003

DO - 10.1016/j.jmva.2019.01.003

M3 - Article

VL - 171

SP - 382

EP - 396

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

ER -