Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis

Selene Yue Xu, Sandahl Nelson, Jacqueline Kerr, Suneeta Godbole, Eileen Johnson, Ruth E. Patterson, Cheryl L. Rock, Dorothy D. Sears, Ian Abramson, Loki Natarajan

Research output: Contribution to journalArticle

Abstract

Accelerometers are person-worn sensors that provide objective measurements of movement based on minute-level activity counts, thus providing a rich framework for assessing physical activity patterns. New statistical approaches and computational tools are needed to exploit these densely sampled time-series data. We implement a functional principal component mixed model approach to ascertain temporal activity patterns in 578 overweight women (60% cancer survivors) and summarize individual patterns with unique personalized principal component scores. We then test if these patterns are associated with health by performing multiple regression of health outcomes (including biomarkers, namely, insulin, C-reactive protein, and quality of life) on activity patterns represented by these scores. Our model elucidates the most important patterns/modes of variation in physical activities. Results show that health outcomes including biomarkers and quality of life are strongly associated with the total volume, as well as temporal variation in activity. In addition, associations between physical activity and health outcomes are not modified by cancer status. Our findings suggest that employing a multilevel functional principal component analysis approach can elicit important temporal patterns in physical activity. It further allows us to study the relationship between health outcomes and activity patterns, and thus could be a valuable modeling approach in behavioral research.

Original languageEnglish (US)
Pages (from-to)403-421
Number of pages19
JournalStatistics in Biosciences
Volume11
Issue number2
DOIs
StatePublished - Jul 15 2019
Externally publishedYes

Fingerprint

Functional Principal Component Analysis
Principal Component Analysis
Principal component analysis
Health
Exercise
Modeling
Biomarkers
Behavioral research
Quality of Life
Behavioral Research
Principal Components
Accelerometers
C-Reactive Protein
Cancer
Survivors
Time series
Neoplasms
Insulin
Accelerometer
Multiple Regression

Keywords

  • Accelerometer
  • Functional method
  • Physical activity patterns
  • Principal component analysis

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry, Genetics and Molecular Biology (miscellaneous)

Cite this

Xu, S. Y., Nelson, S., Kerr, J., Godbole, S., Johnson, E., Patterson, R. E., ... Natarajan, L. (2019). Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis. Statistics in Biosciences, 11(2), 403-421. https://doi.org/10.1007/s12561-019-09237-3

Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis. / Xu, Selene Yue; Nelson, Sandahl; Kerr, Jacqueline; Godbole, Suneeta; Johnson, Eileen; Patterson, Ruth E.; Rock, Cheryl L.; Sears, Dorothy D.; Abramson, Ian; Natarajan, Loki.

In: Statistics in Biosciences, Vol. 11, No. 2, 15.07.2019, p. 403-421.

Research output: Contribution to journalArticle

Xu, SY, Nelson, S, Kerr, J, Godbole, S, Johnson, E, Patterson, RE, Rock, CL, Sears, DD, Abramson, I & Natarajan, L 2019, 'Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis', Statistics in Biosciences, vol. 11, no. 2, pp. 403-421. https://doi.org/10.1007/s12561-019-09237-3
Xu, Selene Yue ; Nelson, Sandahl ; Kerr, Jacqueline ; Godbole, Suneeta ; Johnson, Eileen ; Patterson, Ruth E. ; Rock, Cheryl L. ; Sears, Dorothy D. ; Abramson, Ian ; Natarajan, Loki. / Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis. In: Statistics in Biosciences. 2019 ; Vol. 11, No. 2. pp. 403-421.
@article{fd47760a76c943b6ab7efa0abbb14f32,
title = "Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis",
abstract = "Accelerometers are person-worn sensors that provide objective measurements of movement based on minute-level activity counts, thus providing a rich framework for assessing physical activity patterns. New statistical approaches and computational tools are needed to exploit these densely sampled time-series data. We implement a functional principal component mixed model approach to ascertain temporal activity patterns in 578 overweight women (60{\%} cancer survivors) and summarize individual patterns with unique personalized principal component scores. We then test if these patterns are associated with health by performing multiple regression of health outcomes (including biomarkers, namely, insulin, C-reactive protein, and quality of life) on activity patterns represented by these scores. Our model elucidates the most important patterns/modes of variation in physical activities. Results show that health outcomes including biomarkers and quality of life are strongly associated with the total volume, as well as temporal variation in activity. In addition, associations between physical activity and health outcomes are not modified by cancer status. Our findings suggest that employing a multilevel functional principal component analysis approach can elicit important temporal patterns in physical activity. It further allows us to study the relationship between health outcomes and activity patterns, and thus could be a valuable modeling approach in behavioral research.",
keywords = "Accelerometer, Functional method, Physical activity patterns, Principal component analysis",
author = "Xu, {Selene Yue} and Sandahl Nelson and Jacqueline Kerr and Suneeta Godbole and Eileen Johnson and Patterson, {Ruth E.} and Rock, {Cheryl L.} and Sears, {Dorothy D.} and Ian Abramson and Loki Natarajan",
year = "2019",
month = "7",
day = "15",
doi = "10.1007/s12561-019-09237-3",
language = "English (US)",
volume = "11",
pages = "403--421",
journal = "Statistics in Biosciences",
issn = "1867-1764",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Modeling Temporal Variation in Physical Activity Using Functional Principal Components Analysis

AU - Xu, Selene Yue

AU - Nelson, Sandahl

AU - Kerr, Jacqueline

AU - Godbole, Suneeta

AU - Johnson, Eileen

AU - Patterson, Ruth E.

AU - Rock, Cheryl L.

AU - Sears, Dorothy D.

AU - Abramson, Ian

AU - Natarajan, Loki

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Accelerometers are person-worn sensors that provide objective measurements of movement based on minute-level activity counts, thus providing a rich framework for assessing physical activity patterns. New statistical approaches and computational tools are needed to exploit these densely sampled time-series data. We implement a functional principal component mixed model approach to ascertain temporal activity patterns in 578 overweight women (60% cancer survivors) and summarize individual patterns with unique personalized principal component scores. We then test if these patterns are associated with health by performing multiple regression of health outcomes (including biomarkers, namely, insulin, C-reactive protein, and quality of life) on activity patterns represented by these scores. Our model elucidates the most important patterns/modes of variation in physical activities. Results show that health outcomes including biomarkers and quality of life are strongly associated with the total volume, as well as temporal variation in activity. In addition, associations between physical activity and health outcomes are not modified by cancer status. Our findings suggest that employing a multilevel functional principal component analysis approach can elicit important temporal patterns in physical activity. It further allows us to study the relationship between health outcomes and activity patterns, and thus could be a valuable modeling approach in behavioral research.

AB - Accelerometers are person-worn sensors that provide objective measurements of movement based on minute-level activity counts, thus providing a rich framework for assessing physical activity patterns. New statistical approaches and computational tools are needed to exploit these densely sampled time-series data. We implement a functional principal component mixed model approach to ascertain temporal activity patterns in 578 overweight women (60% cancer survivors) and summarize individual patterns with unique personalized principal component scores. We then test if these patterns are associated with health by performing multiple regression of health outcomes (including biomarkers, namely, insulin, C-reactive protein, and quality of life) on activity patterns represented by these scores. Our model elucidates the most important patterns/modes of variation in physical activities. Results show that health outcomes including biomarkers and quality of life are strongly associated with the total volume, as well as temporal variation in activity. In addition, associations between physical activity and health outcomes are not modified by cancer status. Our findings suggest that employing a multilevel functional principal component analysis approach can elicit important temporal patterns in physical activity. It further allows us to study the relationship between health outcomes and activity patterns, and thus could be a valuable modeling approach in behavioral research.

KW - Accelerometer

KW - Functional method

KW - Physical activity patterns

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=85073654448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073654448&partnerID=8YFLogxK

U2 - 10.1007/s12561-019-09237-3

DO - 10.1007/s12561-019-09237-3

M3 - Article

AN - SCOPUS:85073654448

VL - 11

SP - 403

EP - 421

JO - Statistics in Biosciences

JF - Statistics in Biosciences

SN - 1867-1764

IS - 2

ER -