Stability of exploratory multivariate data modeling in longitudinal data
2003

Stability of Multivariate Data Modeling in Longitudinal Data

Sample size: 2885 publication Evidence: moderate

Author Information

Author(s): Sengul Haydar, Barmada M Michael

Primary Institution: University of Pittsburgh

Hypothesis

How stable are multivariate models when applied to longitudinal data?

Conclusion

The study found good stability in predicted factor models and linkage analysis results over time.

Supporting Evidence

  • Factor models showed high correlations across different time points.
  • Linkage analysis results were consistent with previous studies.
  • Factor analysis helped identify genetic factors related to cardiovascular disease.

Takeaway

The researchers looked at data over many years to see if their models stayed the same, and they found that they did a good job of staying stable.

Methodology

Factor analysis was applied to longitudinal data from the Framingham Heart Study, with adjustments for age and gender.

Limitations

Identifiability issues in factor models and potential numerical instability in early time points.

Participant Demographics

Participants were from the Framingham Heart Study, comprising 4692 subjects from large pedigrees.

Digital Object Identifier (DOI)

10.1186/1471-2156-4-S1-S38

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication