Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Latent variables, measurement error and methods for analysing longitudinal binary and ordinal data.

M Palta1, C Y Lin

  • 1Department of Preventive Medicine, University of Wisconsin-Madison 53705, USA. palta@cornfield.epi.wisc.edu

Statistics in Medicine
|March 10, 1999
PubMed
Summary

Structural equation modeling clarifies differences in longitudinal data analysis, particularly for binary and ordinal outcomes. This approach helps understand measurement error and variability in sleep disorder studies.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Modeling the width and placement of riparian vegetated buffer strips: a case study on the Chi-Jia-Wang stream, Taiwan.

Journal of environmental management·2002
Same author

Evaluation of the Seventh Malaysian Health Plan: a new approach.

Asia-Pacific journal of public health·2002
Same author

Proliferation characteristics of canine transmissible venereal tumor.

Anticancer research·2002
Same author

Oral health assessment by nursing staff of Alzheimer's patients in a long-term-care facility.

Special care in dentistry : official publication of the American Association of Hospital Dentists, the Academy of Dentistry for the Handicapped, and the American Society for Geriatric Dentistry·2002
Same author

Be cautious about choosing a potentially fatal drug for relieving a never-fatal disorder.

Acta paediatrica Taiwanica = Taiwan er ke yi xue hui za zhi·2002
Same author

Sterol efflux mediated by endogenous macrophage ApoE expression is independent of ABCA1.

Arteriosclerosis, thrombosis, and vascular biology·2001

Area of Science:

  • Statistics
  • Biostatistics
  • Psychometrics

Background:

  • Longitudinal data analysis requires careful consideration of between-individual variability and measurement error.
  • Existing methods for longitudinal binary and ordinal data have differing assumptions and interpretations.

Purpose of the Study:

  • To explore structural equations with latent variables for analyzing longitudinal binary and ordinal data.
  • To provide insights into the assumptions and interpretation differences of popular longitudinal data analysis methods.
  • To clarify the distinction between marginal and cluster-specific models and the role of measurement error.

Main Methods:

  • Structural equation modeling (SEM) with continuous latent variables.
  • Comparison of SEM with common longitudinal modeling approaches: marginal models (SAS GEE), generalized linear mixed models (GAUSS), and cluster-specific mixed effects models (MIXOR).

Related Experiment Videos

  • Application to data from a sleep disorder study.

    • Main Results:

    • Structural equation formulation clarifies that marginal and cluster-specific models differ in predicted variable scaling.
    • Adjustment for measurement error in the outcome is shown to involve a change in scale.
    • Comparative analysis of results from different modeling approaches applied to sleep disorder data.

    Conclusions:

    • Structural equations with latent variables offer a unified framework for understanding longitudinal data analysis.
    • The SEM approach enhances clarity on model assumptions, interpretation, and the handling of measurement error.
    • This methodology is valuable for analyzing complex longitudinal binary and ordinal data, as demonstrated in the sleep disorder study.