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

Regression models for mixed Poisson and continuous longitudinal data.

Ying Yang1, Jian Kang, Kai Mao

  • 1Department of Mathematical Sciences, Tsinghua University, Beijing 100084, People's Republic of China. yyang@math.tsinghua.edu.cn

Statistics in Medicine
|November 30, 2006
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

Peroxisome Proliferator-Activated Receptor (PPARγ) Plays a Protective Role in Cigarette Smoking-Induced Inflammation via AMP-Activated Protein Kinase (AMPK) Signaling.

Medical science monitor : international medical journal of experimental and clinical research·2018
Same author

Spatially Adaptive Varying Correlation Analysis for Multimodal Neuroimaging Data.

IEEE transactions on medical imaging·2018
Same author

Superconductivity in FeSe: The Role of Nematic Order.

Physical review letters·2018
Same author

Suppressed expression of Cbl-b by NF-κB mediates icotinib resistance in EGFR-mutant non-small-cell lung cancer.

Cell biology international·2018
Same author

The independence of and associations among apoptosis, autophagy, and necrosis.

Signal transduction and targeted therapy·2018
Same author

Tyrosine kinase inhibitor-induced IL-6/STAT3 activation decreases sensitivity of EGFR-mutant non-small cell lung cancer to icotinib.

Cell biology international·2018

This study introduces flexible regression models to analyze mixed Poisson and continuous data, revealing significant changes in correlation over time. Ignoring heterogeneous variances is cautioned against for accurate modeling and inference.

Area of Science:

  • Biostatistics
  • Statistical Modeling
  • Longitudinal Data Analysis

Background:

  • Mixed Poisson and continuous response data present unique analytical challenges.
  • Understanding the influence of covariates and temporal changes in correlation is crucial.

Purpose of the Study:

  • To develop flexible regression models for mixed Poisson and continuous responses.
  • To evaluate how covariate influence and the correlation between responses change over time.
  • To address scenarios with heterogeneous variance and time-varying correlations.

Main Methods:

  • Jointly building marginal models for mixed responses.
  • Utilizing likelihood ratio tests to detect changes in variance and correlation over time.
  • Applying data transformations when temporal changes are significant.

Related Experiment Videos

Main Results:

  • The proposed flexible regression models effectively handle mixed response types.
  • Significant temporal changes in the correlation between Poisson and continuous responses were observed.
  • Heterogeneous variances were found to be a critical factor in modeling.

Conclusions:

  • Flexible regression models are essential for accurately analyzing mixed Poisson and continuous data with time-varying correlations.
  • Heterogeneous variances must be considered in statistical inference for such data.
  • The methods provide valuable insights for longitudinal studies, such as the ICDB cohort study.