Covariate Dependent Sparse Functional Data Analysis

Minhee Kim (), Todd Allen () and Kaibo Liu ()
Additional contact information
Minhee Kim: Department of Industrial and Systems Engineering, University of Florida, Gainesville, Florida 32611
Todd Allen: Department of Nuclear Engineering and Radiological Sciences, University of Michigan, Ann Arbor, Michigan 48109
Kaibo Liu: Department of Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, Wisconsin 53706

INFORMS Joural on Data Science, 2023, vol. 2, issue 1, 81-98

Abstract: This study proposes a method to incorporate covariate information into sparse functional data analysis. The method aims at cases where each subject has a limited number of longitudinal measurements and is associated with static covariates. This research is motivated by several use cases in practice. One representative example is void swelling, a nuclear-specific material degradation mechanism. Void swelling is affected by many covariates, including alloy composition and irradiation type. How to accurately model the complicated joint effects of such covariates on the swelling process is the key to mitigating the effect of swelling and ensuring safe operation. Unlike most of the existing methods, the proposed method can handle high-dimensional covariates with the informative covariate identification procedure and sparse and irregularly spaced measurements, that is, does not require complete or dense observations. The main innovation of the proposed method is that we model the variation coming from covariates and the variation left conditioned on covariates, such that the functional principal component analysis and Gaussian process can be conducted in a unified manner. We also propose a systematic approach to identify important covariates in the hypothesis testing context. The methodology is demonstrated on applications in nuclear engineering and healthcare and simulation studies.

Keywords: functional data analysis; functional principal component analysis; covariate identification; Gaussian process (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/ijds.2023.0025 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orijds:v:2:y:2023:i:1:p:81-98

Access Statistics for this article

More articles in INFORMS Joural on Data Science from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().