In: Statistics and Probability
Verification and Validation of Simulation Models
3. How to build a model that is well connected with the verification and validation process?
4. What is meant by calibration, and what is the process of calibration so that it can obtain a model that means to be used for simulation?
3. V & V techniques can be used. V&V Techniques
• Informal V&V techniques are among the most commonly used. They are called informal because their tools and approaches rely heavily on human reasoning and subjectivity without stringent mathematical formalism.
• Static V&V techniques assess the accuracy of the static model design and source code. Static techniques do not require machine execution of the model, but mental execution can be used. The techniques are very popular and widely used, and many automated tools are available to assist in the V&V process. Static techniques can reveal a variety of information about the structure of the model, the modeling techniques used, data and control flow within the model, and syntactical accuracy (Whitner and Balci, 1989).
4. Calibration involves the optimization of a subset of model parameters to improve the fit of model predictions to empirical data. Traditionally, calibration is distinguished from other estimation tasks by its use to obtain estimates for parameters for which only indirect data is available. For example, in microsimulation models of cancer in humans, parameters for which direct empirical data are unavailable (e.g., growth rates of preclinical cancers) are determined by selecting input rate values to produce model outputs (e.g., cancer incidence rates, which are functionally dependent on the parameters for which direct data are unavailable) that “are as close as possible” to empirical data.