7. Parameter Estimation and Predictive Uncertainty

Summary

This chapter contains sections titled:

• Model Calibration or Conditioning

• Parameter Response Surfaces and Sensitivity Analysis

• Performance Measures and Likelihood Measures

• Automatic Optimisation Techniques

• Recognising Uncertainty in Models and Data: Forward Uncertainty Estimation

• Types of Uncertainty Interval

• Model Calibration Using Bayesian Statistical Methods

• Dealing with Input Uncertainty in a Bayesian Framework

• Model Calibration Using Set Theoretic Methods

• Recognising Equifinality: The GLUE Method

• Case Study: An Application of the GLUE Methodology in Modelling the Saeternbekken MINIFELT Catchment, Norway

• Case Study: Application of GLUE Limits of Acceptability Approach to Evaluation in Modelling the Brue Catchment, Somerset, England

• Other Applications of GLUE in Rainfall–Runoff Modelling

• Comparison of GLUE and Bayesian Approaches to Uncertainty Estimation

• Predictive Uncertainty, Risk and Decisions

• Dynamic Parameters and Model Structural Error

• Quality Control and Disinformation in Rainfall–Runoff Modelling

• The Value of Data in Model Conditioning

• Key Points from Chapter 7

• Likelihood Measures for use in Evaluating Models

• Combining Likelihood Measures

• Defining the Shape of a Response or Likelihood Surface