Download
Find here the model, code, and example results of parameter fitting/calibration and sensitivity analysis for an agent-based model using NetLogo and R.
The corresponding manuscript is published in Journal of Artificial Societies and Social Simulation as:
Thiele JC, Kurth W, Grimm V (2014): Facilitating parameter estimation and sensitivity analysis of agent-based models: a cookbook using NetLogo and R. <http://jasss.soc.surrey.ac.uk/xx/x/x.html>
Methods/Techniques used are:
a. Parameter fitting:
1. Full Factorial Design
2. Simple Random Sampling
3. Latin Hypercube Sampling
4. Quasi-Newton Method
5. Simulated Annealing
6. Genetic Algorithm
7. Approximate Bayesian Computation
b. Sensitivity Analysis:
1. Local SA
2. Morris Screening
3. DoE
4. Partial (Rank) Correlation Coefficient
5. Standardised (Rank) Regression Coefficient
6. Sobol'
7. eFAST
8. FANOVA Decomposition
Have also a look on our other projects: http://www.uni-goettingen.de/de/315075.html
Project Samples
