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 models for autocorrelated count data.

Kerrie P Nelson1, Brian G Leroux

  • 1Department of Statistics, University of South Carolina, Columbia, SC 29208, USA. kerrie@stat.sc.edu

Statistics in Medicine
|October 1, 2005
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

Validation of a colorectal cancer risk prediction model in US Black women.

Cancer prevention research (Philadelphia, Pa.)·2026
Same author

Referrals to Child Protective Services for pediatric emergency department patients after falls.

Child abuse & neglect·2026
Same author

Diagnostic accuracy analysis for multiple raters using probit hierarchical model for ordinal ratings.

Statistical methods in medical research·2025
Same author

Outcomes and engagement among Spanish- versus English-speaking participants in a remote postpartum blood pressure monitoring program.

American journal of obstetrics & gynecology MFM·2025
Same author

Accounting for Patient Characteristics in a Model-Based Kappa of Agreement Between Two Experts' Ordinal Ratings.

Statistics in medicine·2025
Same author

Differences in language used to describe racial groups in emergency medicine standardized letter of evaluation.

AEM education and training·2025
Same journal

Optimal Weighted Tests for Replication Studies and the 'Two-Trials Rule' With Multiple Hypotheses.

Statistics in medicine·2026
Same journal

Identifiable Copula-Double-Cox Models: A Fully Parametric Framework for Dependent Right-Censored Survival Data.

Statistics in medicine·2026
Same journal

Moving From Individualized Risk-Based Prevention to Benefit-Based Prevention: Estimating Individualized Life-Years Gained From Prevention Services as a Basis for Eligibility.

Statistics in medicine·2026
Same journal

A Mixture of Distributed Lag Non-Linear Models to Account for Spatially Heterogeneous Exposure-Lag-Response Associations.

Statistics in medicine·2026
Same journal

Practical Considerations for Gaussian Process Modeling for Causal Inference in Quasi-Experimental Studies With Panel Data.

Statistics in medicine·2026
Same journal

Covariate Adjustment for Wilcoxon Two Sample Statistic and Test.

Statistics in medicine·2026
See all related articles

Different methods for generalized linear mixed models yield varying parameter estimates and standard errors, especially for random effects. These differences impact count data analysis but result in similar future predictions.

Area of Science:

  • Biostatistics
  • Statistical Modeling

Background:

  • Generalized linear mixed models (GLMMs) are widely used for correlated, non-normal data.
  • Various fitting methods exist, including Monte-Carlo Markov Chain (MCMC) and Penalized Quasi-Likelihood (PQL).

Purpose of the Study:

  • To compare parameter estimation accuracy of different GLMM fitting methods.
  • To analyze polio incidence data (1970-1983) using a longlinear GLMM with autoregressive correlation.

Main Methods:

  • Comparison of parameter estimation from MCMC, PQL, and iterative bias correction methods.
  • Application of a longlinear generalized linear mixed model with an autoregressive correlation structure.
  • A small simulation study to investigate estimation differences.

Main Results:

Related Experiment Videos

  • Substantial differences in parameter estimates and standard errors were observed across methods.
  • Estimation of random effects distribution parameters showed particular variability.
  • Despite differences, all methods produced reasonably similar predictions for future observations.

Conclusions:

  • The choice of GLMM fitting method can significantly influence parameter estimation, especially for random effects.
  • While parameter estimates vary, predictive performance for future counts is largely consistent across methods.