Alphabetic Criteria

OED Alphabetic criteria are based on summaries of the Fisher information matrix. In the context of Bayesian OED, these criteria summarize the posterior uncertainty. The most commonly used are A Optimality Criteria and D Optimality Criteria which are defined as the trace, and the determinant, of the posterior covariance, respectively. Each of the commonly known alphabetic criteria is (or will be) implemented with different variations for maximum flexibility.

A Optimality Criteria

• A-optimality
  • Bayesian A Optimality Criterion (Binary Design)
  • Relaxed Bayesian A Optimality Criterion (Binary or Relaxed Design)
  • Robust Bayesian A Optimality

D Optimality Criteria

• D-optimality
  • Bayesian D Optimality Criterion (Binary Design)
  • Relaxed Bayesian D Optimality Criterion (Binary or Relaxed Design)
  • Robust Bayesian D Optimality