A bayesian population model with hierarchical mixture priors applied to blood count data

Peter Müller, Gary L. Rosner

Research output: Contribution to journalArticlepeer-review

83 Scopus citations


Population pharmacokinetic and pharmacodynamic studies require analyzing nonlinear growth curves fit to multiple measurements from study subjects. We propose a class of nonlinear population models with nonparametric second-stage priors for analyzing such data. The proposed models apply a flexible class of mixtures to implement the nonparametric second stage. The discussion is based on a pharmacodynamic study involving longitudinal data consisting of hematologic profiles (i.e., blood counts measured over time) of cancer patients undergoing chemotherapy. We describe a full posterior analysis in a Bayesian framework. This includes prediction of future observations (profiles and end points for new patients), estimation of the mean response function for observed individuals, and inference on population characteristics. The mixture model is specified and given a hyperprior distribution by means of a Dirichlet processes prior on the mixing measure. Estimation is implemented by a combination of various Markov chain Monte Carlo schemes, including a novel independence chain scheme for a logistic regression. The discussion is motivated by a pharmacodynamic case study; however, the concepts are more generally applicable to the wider class of population models.

Original languageEnglish (US)
Pages (from-to)1279-1292
Number of pages14
JournalJournal of the American Statistical Association
Issue number440
StatePublished - Dec 1 1997
Externally publishedYes


  • Dirichlet process
  • Longitudinal data
  • Nonparametric modeling
  • Pharmacodynamics
  • Pharmacokinetics
  • Repeated measurements

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'A bayesian population model with hierarchical mixture priors applied to blood count data'. Together they form a unique fingerprint.

Cite this