Time series analysis and its relationship with longitudinal analysis

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper discusses the relationship between longitudinal analysis of inter-individual (co-)variation and time series analysis of intra-individual (co-)variation. To set the stage for this discussion, first a tutorial overview of modern techniques of multivariate time series analysis is given which highlights the central role of rate-space modeling. Some increasingly general instances of the state-spuce model are presented, followed by a concise description of two recent applications involving nonlinear state-space modeling of oscillatory finger motion and nonlinear growth, respectively. We then consider the question under which conditions longitudinal factor analysis of inter-individual covariation will yield the same results as dynamic factor analysis of single-subject time series data. The conditions concerned can be derived from ergodicity theory and turn out to be very restrictive. This implies that the results obtained in analyses of inter-individual variation (like the construction and validation of measurement scales) cannot be generalized to the assessment and prediction of individual developmental processes (e.g., in single-subject conseling). A simple illustration with simulated data is given, to the best of our knowledge for the first time, in which a factor analysis of inter-individual covariation yields a satisfactorily fitting solution that has no relationship whatsoever to the factor structures characterizing the intra-individual covariation of each subject in the sample.

Original languageEnglish (US)
Pages (from-to)S232-S237
JournalInternational Journal of Sports Medicine, Supplement
Volume18
Issue numberSUPPL. 3
StatePublished - Dec 1 1997

Fingerprint

Statistical Factor Analysis
Fingers
Growth

All Science Journal Classification (ASJC) codes

  • Physiology
  • Public Health, Environmental and Occupational Health
  • Cardiology and Cardiovascular Medicine

Cite this

@article{69a2e74f87794b068460aaa234d25cd9,
title = "Time series analysis and its relationship with longitudinal analysis",
abstract = "This paper discusses the relationship between longitudinal analysis of inter-individual (co-)variation and time series analysis of intra-individual (co-)variation. To set the stage for this discussion, first a tutorial overview of modern techniques of multivariate time series analysis is given which highlights the central role of rate-space modeling. Some increasingly general instances of the state-spuce model are presented, followed by a concise description of two recent applications involving nonlinear state-space modeling of oscillatory finger motion and nonlinear growth, respectively. We then consider the question under which conditions longitudinal factor analysis of inter-individual covariation will yield the same results as dynamic factor analysis of single-subject time series data. The conditions concerned can be derived from ergodicity theory and turn out to be very restrictive. This implies that the results obtained in analyses of inter-individual variation (like the construction and validation of measurement scales) cannot be generalized to the assessment and prediction of individual developmental processes (e.g., in single-subject conseling). A simple illustration with simulated data is given, to the best of our knowledge for the first time, in which a factor analysis of inter-individual covariation yields a satisfactorily fitting solution that has no relationship whatsoever to the factor structures characterizing the intra-individual covariation of each subject in the sample.",
author = "Molenaar, {Peter C.M.}",
year = "1997",
month = "12",
day = "1",
language = "English (US)",
volume = "18",
pages = "S232--S237",
journal = "International Journal of Sports Medicine, Supplement",
issn = "0943-917X",
publisher = "Georg Thieme Verlag",
number = "SUPPL. 3",

}

Time series analysis and its relationship with longitudinal analysis. / Molenaar, Peter C.M.

In: International Journal of Sports Medicine, Supplement, Vol. 18, No. SUPPL. 3, 01.12.1997, p. S232-S237.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Time series analysis and its relationship with longitudinal analysis

AU - Molenaar, Peter C.M.

PY - 1997/12/1

Y1 - 1997/12/1

N2 - This paper discusses the relationship between longitudinal analysis of inter-individual (co-)variation and time series analysis of intra-individual (co-)variation. To set the stage for this discussion, first a tutorial overview of modern techniques of multivariate time series analysis is given which highlights the central role of rate-space modeling. Some increasingly general instances of the state-spuce model are presented, followed by a concise description of two recent applications involving nonlinear state-space modeling of oscillatory finger motion and nonlinear growth, respectively. We then consider the question under which conditions longitudinal factor analysis of inter-individual covariation will yield the same results as dynamic factor analysis of single-subject time series data. The conditions concerned can be derived from ergodicity theory and turn out to be very restrictive. This implies that the results obtained in analyses of inter-individual variation (like the construction and validation of measurement scales) cannot be generalized to the assessment and prediction of individual developmental processes (e.g., in single-subject conseling). A simple illustration with simulated data is given, to the best of our knowledge for the first time, in which a factor analysis of inter-individual covariation yields a satisfactorily fitting solution that has no relationship whatsoever to the factor structures characterizing the intra-individual covariation of each subject in the sample.

AB - This paper discusses the relationship between longitudinal analysis of inter-individual (co-)variation and time series analysis of intra-individual (co-)variation. To set the stage for this discussion, first a tutorial overview of modern techniques of multivariate time series analysis is given which highlights the central role of rate-space modeling. Some increasingly general instances of the state-spuce model are presented, followed by a concise description of two recent applications involving nonlinear state-space modeling of oscillatory finger motion and nonlinear growth, respectively. We then consider the question under which conditions longitudinal factor analysis of inter-individual covariation will yield the same results as dynamic factor analysis of single-subject time series data. The conditions concerned can be derived from ergodicity theory and turn out to be very restrictive. This implies that the results obtained in analyses of inter-individual variation (like the construction and validation of measurement scales) cannot be generalized to the assessment and prediction of individual developmental processes (e.g., in single-subject conseling). A simple illustration with simulated data is given, to the best of our knowledge for the first time, in which a factor analysis of inter-individual covariation yields a satisfactorily fitting solution that has no relationship whatsoever to the factor structures characterizing the intra-individual covariation of each subject in the sample.

UR - http://www.scopus.com/inward/record.url?scp=0030808311&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030808311&partnerID=8YFLogxK

M3 - Article

C2 - 9272854

AN - SCOPUS:0030808311

VL - 18

SP - S232-S237

JO - International Journal of Sports Medicine, Supplement

JF - International Journal of Sports Medicine, Supplement

SN - 0943-917X

IS - SUPPL. 3

ER -