Yet another MAUP: how agent-based model uncertainty and sensitivity are space-dependent
نویسنده
چکیده
This paper evaluates the spatial dimension of agent-based model uncertainty and sensitivity. Monte Carlo simulations are carried out, leading to distributions of results, recorded for each agent. The results are aggregated into zones of varying shape and size. Output variance decomposition is performed on the zones in order to quantify model sensitivity to every input. For every zone, inputs that have maximum impact on output variability are identified and rendered using maps of dominant factors. The maps are then compared among different aggregation schemes to demonstrate how model sensitivity changes with the change in shape and size of the zones.
منابع مشابه
Joint optimization of pricing and capacity allocation for two competitive airlines under demand uncertainty
Nowadays, airline industries should overcome different barriers regarding the fierce competition and changing consumer behavior. Thus, they attempt to focus on joint decision making which enables them to set pricing and capacity allocation to maximize their profits. In this research, we develop a model to optimize pricing and capacity allocation in a duopoly of single-flight leg for two competi...
متن کاملMultiscale Spatial Sensitivity Analysis for Agent- Based Modelling of Coupled Landscape and Aquatic Systems
Models of coupled landscape and aquatic systems (CLAS) are prone to input uncertainties that vary over space. To address this challenge, we employ a comprehensive model evaluation that: [1] quantifies the variability of model results (uncertainty analysis), and [2] decomposes this variability based on the relative contribution of inputs to identify major drivers in the model (sensitivity analys...
متن کاملSpatial, Temporal and Social Scaling in Sparsely Populated Areas – Geospatial Mapping and Simulation Techniques to Investigate Social Diversity
Scale-dependence is a well-known phenomenon in geography with sophisticated theoretical approaches and techniques at hand to deal with the modifiable areal unit problem (MAUP). Geographical analyses are, however, predominantly focusing on urban spaces with a high level of small-scaled social diversity. While space is considered scale-sensitive less attention is paid to scale in a temporal and s...
متن کاملDynamic Model Updating in Simulation with Multimodels: A Taxonomy and a Generic Agent-Based Architecture
Dynamic model update and replacement are critical capabilities for modeling problems, the underlying processes of which are uncertain. The trajectory of most complex social phenomena, including conflicts, for instance, is never fixed and predictable. Symbiotic simulation is yet another emergent challenge that requires model adaptivity in response to emerging conditions within the actual system....
متن کاملA joint pricing-network design model for a resilient closed-loop supply chain under quantity discount
In this paper, a novel resilient multi-echelon closed-loop location-allocation-inventory problem (RMCLIP) is addressed that optimizes strategic and tactical decisions simultaneously. In order to represent the purchasing cost of raw material from the supplier, a pricing model under quantity discounts is employed in the closed-loop supply chain (CLSC). Considering the capability of returning the ...
متن کامل