A combined multilevel factor analysis and covariance regression model with mixed effects in the mean and variance structure

Author:

Orindi Benedict12ORCID,Quintero Adrian3,Bruyneel Luk4,Li Baoyue5,Lesaffre Emmanuel1

Affiliation:

1. Leuven Biostatistics and Statistical Bioinformatics Centre KU Leuven Leuven Belgium

2. Department of Statistics KEMRI‐Wellcome Trust Research Programme – CGRMC Kilifi Kenya

3. Evaluation Department Icfes – Colombian Institute for Educational Evaluation Bogota Colombia

4. Leuven Institute for Healthcare Policy KU Leuven Leuven Belgium

5. Biometrics Division IMPACT Therapeutics Shanghai China

Abstract

Li et al developed a multilevel covariance regression (MCR) model as an extension of the covariance regression model of Hoff and Niu. This model assumes a hierarchical structure for the mean and the covariance matrix. Here, we propose the combined multilevel factor analysis and covariance regression model in a Bayesian framework, simultaneously modeling the MCR model and a multilevel factor analysis (MFA) model. The proposed model replaces the responses in the MCR part with the factor scores coming from an MFA model. Via a simulation study and the analysis of real data, we show that the proposed model is quite efficient when the responses of the MCR model are not measured directly but are latent variables such as the patient experience measurements in our motivating dataset.

Funder

FP7 Health

Publisher

Wiley

Subject

Statistics and Probability,Epidemiology

Reference56 articles.

1. The Matrix-Logarithmic Covariance Model

2. ORDINAL REGRESSION METHODOLOGY FOR ROC CURVES DERIVED FROM CORRELATED DATA

3. Joint mean-covariance models with applications to longitudinal data: unconstrained parameterisation

4. Modeling covariance matrices in terms of standard deviations and correlations, with application to shrinkage;Barnard J;Stat Sin,2000

5. Nonparametric covariance model;Yin J;Stat Sin,2010

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3