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

Repeated measures for two within-subject factors: analysis and missing data solutions

R C Schoemaker1, H C van Houwelingen

  • 1Centre for Human Drug Research, Leiden, The Netherlands.

Journal of Biopharmaceutical Statistics
|July 1, 1994
PubMed
Summary
This summary is machine-generated.

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

Vertical modelling: Analysis of competing risks data with missing causes of failure.

Statistical methods in medical research·2011
Same author

The effects of TPA023, a GABAAα2,3 subtype-selective partial agonist, on essential tremor in comparison to alcohol.

Journal of psychopharmacology (Oxford, England)·2011
Same author

The effects of a novel histamine-3 receptor inverse agonist on essential tremor in comparison to stable levels of alcohol.

Journal of psychopharmacology (Oxford, England)·2011
Same author

Orexin receptor antagonism, a new sleep-promoting paradigm: an ascending single-dose study with almorexant.

Clinical pharmacology and therapeutics·2010
Same author

Comparing and ranking hospitals based on outcome: results from The Netherlands Stroke Survey.

QJM : monthly journal of the Association of Physicians·2009
Same author

Pharmacokinetics, pharmacodynamics and the pharmacokinetic/ pharmacodynamic relationship of zolpidem in healthy subjects.

Journal of psychopharmacology (Oxford, England)·2009

Restricted maximum likelihood (REML) methodology is a superior statistical analysis for repeated measures designs with missing data in clinical pharmacology compared to imputation. REML provides an elegant and correctable tool for analyzing such complex data.

Area of Science:

  • Biostatistics
  • Clinical Pharmacology
  • Statistical Modeling

Background:

  • Repeated measures designs with two within-subject factors are common in clinical pharmacology.
  • Missing data in these designs pose significant analytical challenges.
  • Traditional imputation methods can yield problematic and uncorrectable results.

Purpose of the Study:

  • To compare the efficacy of restricted maximum likelihood (REML) methodology against imputation procedures for analyzing repeated measures designs with missing data.
  • To evaluate the performance of these methods in small sample situations.
  • To demonstrate the utility of REML in clinical pharmacology research.

Main Methods:

  • The study employed simulations to illustrate the statistical analysis of a repeated measures design.

Related Experiment Videos

  • Restricted maximum likelihood (REML) methodology was applied.
  • An imputation procedure was used as a comparative method.
  • Test statistics were compared to an F-distribution for REML analysis.

    • Main Results:

    • Imputation procedures resulted in undesirable outcomes that were difficult to correct.
    • REML estimation provided accurate and manageable results.
    • The simulations highlighted the advantages of REML in handling missing data within the specified design.

    Conclusions:

    • Restricted maximum likelihood (REML) is an elegant and effective statistical tool for the analysis of repeated measures designs with missing data in clinical pharmacology.
    • REML offers a more robust and correctable approach compared to imputation methods, especially in small samples.
    • The findings support the adoption of REML for complex clinical pharmacology study designs.