Show simple item record

A latent factor linear mixed model for high-dimensional longitudinal data analysis.

dc.contributor.author Yang, Qing
dc.contributor.author An, Xinming
dc.contributor.author Bentler, Peter M
dc.date.accessioned 2018-05-08T16:26:37Z
dc.date.available 2018-05-08T16:26:37Z
dc.date.issued 2013-10
dc.identifier.issn 0277-6715
dc.identifier.issn 1097-0258
dc.identifier.uri https://hdl.handle.net/10161/16701
dc.description.abstract High-dimensional longitudinal data involving latent variables such as depression and anxiety that cannot be quantified directly are often encountered in biomedical and social sciences. Multiple responses are used to characterize these latent quantities, and repeated measures are collected to capture their trends over time. Furthermore, substantive research questions may concern issues such as interrelated trends among latent variables that can only be addressed by modeling them jointly. Although statistical analysis of univariate longitudinal data has been well developed, methods for modeling multivariate high-dimensional longitudinal data are still under development. In this paper, we propose a latent factor linear mixed model (LFLMM) for analyzing this type of data. This model is a combination of the factor analysis and multivariate linear mixed models. Under this modeling framework, we reduced the high-dimensional responses to low-dimensional latent factors by the factor analysis model, and then we used the multivariate linear mixed model to study the longitudinal trends of these latent factors. We developed an expectation-maximization algorithm to estimate the model. We used simulation studies to investigate the computational properties of the expectation-maximization algorithm and compare the LFLMM model with other approaches for high-dimensional longitudinal data analysis. We used a real data example to illustrate the practical usefulness of the model.
dc.language eng
dc.relation.ispartof Statistics in medicine
dc.relation.isversionof 10.1002/sim.5825
dc.subject Humans
dc.subject Data Interpretation, Statistical
dc.subject Factor Analysis, Statistical
dc.subject Linear Models
dc.subject Longitudinal Studies
dc.subject Cognition
dc.subject Algorithms
dc.subject Physical Fitness
dc.subject Aged
dc.subject Female
dc.subject Male
dc.title A latent factor linear mixed model for high-dimensional longitudinal data analysis.
dc.type Journal article
dc.date.updated 2018-05-08T16:26:35Z
pubs.issue 24
pubs.organisational-group School of Nursing
pubs.organisational-group Duke
pubs.publication-status Published
pubs.volume 32
duke.contributor.orcid Yang, Qing|0000-0003-4844-4690


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record