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

Statistical methods for longitudinal research on bipolar disorders.

John Hennen1

  • 1Consolidated Department of Psychiatry, Harvard Medical School and McLean Hospital, Belmont, MA 02478, USA. jhennen@mclean.org

Bipolar Disorders
|June 5, 2003
PubMed
Summary

Longitudinal studies are crucial for bipolar disorder outcomes research. Statistical methods like summary statistics, random effects modeling, GEE, and survival analysis effectively handle repeated measures and missing data in bipolar disorder research.

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

Mr. Hennen's Case of Profuse Epistaxis.

The Medical and physical journal·2018
Same author

Mr. Hennen, on the Use of Sponge in Ophthalmia.

The Medical and physical journal·2018
Same author

Additional Observations on the Cure of Syphilis without Mercury.

Edinburgh medical and surgical journal·2018
Same author

An Account of the Eruptive Diseases Which Have Lately Appeared in the Military Hospitals of Edinburgh, Both Naturally and after Inoculation, &c.

Edinburgh medical and surgical journal·2018
Same author

Observations on the Cure of Syphilis without Mercury, &c.

Edinburgh medical and surgical journal·2018
Same author

Case of Hydrothorax, Complicated with Disease of the Heart and Lungs.

Edinburgh medical and surgical journal·2018

Area of Science:

  • Psychiatric research
  • Biostatistics
  • Clinical trial design

Background:

  • Bipolar disorder research presents challenges due to complex clinical variations over time.
  • Longitudinal studies with large samples and repeated outcome measures are essential.

Purpose of the Study:

  • To review statistical methods suitable for longitudinal outcomes research in bipolar disorders.
  • To address the complexities of repeated measures data and missing data in clinical trials.

Main Methods:

  • Review of analytic methods for repeated measures data, including endpoint analysis, summary statistics, random/mixed effects modeling, generalized estimating equations (GEE), and survival analyses.
  • Illustration of methods using data from randomized, double-blind studies on acute mania.

Related Experiment Videos

Main Results:

  • Four methods are particularly suitable for repeated measures data in bipolar disorder studies: summary statistic method, random/mixed effects modeling, GEE regression modeling, and survival analysis.
  • These methods were applied to outcome measures like change in Young Mania Rating Scale (YMRS) scores and clinical response rates.

Conclusions:

  • Longitudinal study designs with frequent data collection over extended periods and large sample sizes are ideal for bipolar disorder outcomes research.
  • Statistical methods must be capable of accommodating missing data, which is expected in such studies.