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

Small sample inference for fixed effects from restricted maximum likelihood

M G Kenward1, J H Roger

  • 1Institute of Mathematics and Statistics, University of Kent, Canterbury, U.K.

Biometrics
|October 23, 1997
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

Multiple imputation methods for bivariate outcomes in cluster randomised trials.

Statistics in medicine·2016
Same author

Maternal diet during pregnancy and lactation and cow's milk allergy in offspring.

European journal of clinical nutrition·2016
Same author

Maternal intake of fatty acids and their food sources during lactation and the risk of preclinical and clinical type 1 diabetes in the offspring.

Acta diabetologica·2015
Same author

Response to comments by Seaman et al. on "Analysis of longitudinal trials with protocol deviation: a framework for relevant, accessible assumptions, and inference via multiple imputation," Journal of Biopharmaceutical Statistics 23:1352-1371.

Journal of biopharmaceutical statistics·2014
Same author

Introduction of complementary foods in infancy and atopic sensitization at the age of 5 years: timing and food diversity in a Finnish birth cohort.

Allergy·2013
Same author

Methods for dealing with time-dependent confounding.

Statistics in medicine·2012
Same journal

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
See all related articles

This study introduces a new scaled Wald statistic for Restricted Maximum Likelihood (REML) analyses. This improved method offers better precision and inference in small sample settings, addressing limitations of conventional approaches.

Area of Science:

  • Statistics
  • Statistical Modeling
  • Mixed Models

Background:

  • Restricted Maximum Likelihood (REML) is standard for Gaussian linear models with structured covariance matrices, especially mixed linear models.
  • Conventional inference relies on asymptotic distributions, which can be inaccurate in small samples.
  • Existing methods may lack precision for fixed effects in small-sample REML analyses.

Purpose of the Study:

  • To develop a more accurate statistical inference method for REML in small sample sizes.
  • To improve the estimation of precision and inference for fixed effects in mixed models.
  • To provide a robust alternative to conventional asymptotic-based methods.

Main Methods:

  • Introduction of a scaled Wald statistic.
  • Development of an F approximation for the sampling distribution of the statistic.

Related Experiment Videos

  • Utilizing an adjusted covariance matrix estimator to reduce small-sample bias.
  • Assessment via simulation studies and practical examples.

    • Main Results:

    • The proposed scaled Wald statistic performs well in various small sample settings.
    • The adjusted covariance matrix estimator reduces small-sample bias.
    • The method accurately reproduces exact statistics and F distributions in specific cases (e.g., Hotelling T2, ANOVA F-ratios).

    Conclusions:

    • The new scaled Wald statistic and F approximation offer improved reliability for REML inference, particularly in small samples.
    • This approach enhances the accuracy of precision estimates and fixed effects inference.
    • The method provides a valuable tool for statistical analyses where sample sizes are limited.