Descriptive output validation

A preliminary check to ensure the ABM generates outputs that are broadly in line with our understanding of the real system.

Introduction

  • Validation Process: Compares the model's output for these characteristics with the real-world data. This might involve:

    • Visual comparisons (e.g., comparing simulated population distribution maps with real-world data)
    • Statistical tests to assess the similarity between model outputs and observed data

Explanation

How well can the model output capture the features of the data used to build the model?

Examples

In a weather forecase model, descriptive validation would check if the model predicts sunny or rainy days that are generally consistent with the historical weather patterns of the location.

In a traffic flow model, descriptive output validation might compare the simulated number of vehicles on specific roads during rush hour with actual traffic data collected from sensors.

Outgoing relations

  • Descriptive output validation is a kind of Validation