WORKSHOP OUTLINE

 

WORKSHOP OUTLINE

 

  • Part I

    • Fundamental Concepts I
      • Model Basics
        • Required Elements of a GLMM
        • Exponential Family Likelihood and Quasi-Likelihood
        • Conditional and Marginal Distributions and their role in GLMM
      • Estimation Basics
        • Pseudo-likelihood
        • Integral Approximation (Laplace and Adaptive Quadrature)
      • Inference Basics
    • Fundamental Concepts II
      • GLMM-based Planning Overview
      • Precision Analysis
      • Power and Sample Size
  • Part II

    • Counts
      • Overview of Modeling Issues with Discrete Counts
      • Poisson models
      • Negative Binomial models
    • Proportions
      • Discrete proportions I: Binomial GLMMs
      • Continuous proportions: Beta GLMMs
      • Discrete proportions II: beta-binomial GLMMs
      • Multinomial GLMMs
    • Time-to-Event
      • Gamma GLMMs
      • Survival

 

  • Part III

    • Prediction
      • Best Linear Unbiased Predictor (BLUP)
        • Multi-location
        • Shelf-life
      • Trial and test prediction with GLMMs
    • Repeated Measures
      • Review of Repeated Measures for Gaussian data
      • How non-Gaussian repeated measures differ
      • Conditional broad inference with non-Gaussian repeated measures
      • Marginal inference for non-Gaussian repeated measures
    • Spatial
      • Review of Spatial methods
      • Spatial GLMMs

 

  • Part IV

    • Planning Part II
      • GLMM methods to compare candidate designs
      • GLMM methods for precision and power analysis with repeated measures
    • Using simulation to inform best practices
      • What we know, what we thought we knew (but didn’t really) and what we still don’t know
      • Using simulation to compare candidate GLMM methods
      • Using simulation to augment precision and power analysis
    • Variable selection with GLMMs