Marginal modeling of multilevel binary data with time-varying covariates

Diana L Miglioretti, Patrick J. Heagerty

Research output: Contribution to journalArticlepeer-review

55 Scopus citations


We propose and compare two approaches for regression analysis of multilevel binary data when clusters are not necessarily nested: a GEE method that relies on a working independence assumption coupled with a three-step method for obtaining empirical standard errors, and a likelihood-based method implemented using Bayesian computational techniques. Implications of time-varying endogenous covariates are addressed. The methods are illustrated using data from the Breast Cancer Surveillance Consortium to estimate mammography accuracy from a repeatedly screened population.

Original languageEnglish (US)
Pages (from-to)381-398
Number of pages18
Issue number3
StatePublished - Jul 2004
Externally publishedYes


  • Conditional
  • Endogeneity
  • Hierarchical models
  • Longitudinal data
  • Marginal
  • Transition models

ASJC Scopus subject areas

  • Medicine(all)
  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'Marginal modeling of multilevel binary data with time-varying covariates'. Together they form a unique fingerprint.

Cite this