Pomic: Pattern Oriented Modelling Information Criterion
Calculations of an information criterion are proposed to check the quality of simulations results of ABM/IBM or other non-linear rule-based models. The POMDEV measure is based on the KL divergence and likelihood theory. It basically indicates the deviance of simulation results from field observations. Once POMDEV scores and metropolis-hasting sampling on different model versions are effectuated, POMIC scores can be calculated. This method is still under development and further work are needed for the incorporation of multiple patterns assessment.
- Cyril Piou [aut, cre]
- Date of publication
- 2016-05-20 22:36:55
- Cyril Piou <email@example.com>
- POMDEV calculation for numerical patterns as well as other...
- Pattern Oriented Modeling Information Criterion for ABM/IBM
Files in this package