A Taxonomy of Inference in Simulation Models

Abstract

Simulation models have become increasingly popular in economics in the last two decades, because they can deal with a wide range of research questions. The set-up and analysis of simulation models can range from very specific to very general and can be underpinned by different combinations of theoretical considerations and empirical data. We offer a taxonomy of existing simulation approaches and show how their results can be used to explain observed economic features, examine economic systems and predict future economic processes. Moreover, we offer a new type of method that helps to better exploit empirical findings in simulation models.

Determinants of Unemployment in Swaziland

“…According to Barreto and Howland (2006), the word simulation means the construction of an artificial model of a real system to study and understand the system. According to Brenner and Werker (2007) simulation models are characterized by approximately two factors which are implications and assumptions. The assumptions factor encompasses the premises, definitions and the boundaries for the model for example, the country setting or the time period.…”

Agent-based Modeling for Decision Making in Economics under Uncertainty

“…Concretely, we use an ABM as a research instrument to discover and formulate hypotheses on the behavior of real-world agents that render particular empirical realities (cf. Axelrod, 2007;Brenner and Werker, 2007). As such, ABMs can be used for economic theorizing.…”

“…We use ABMs in research to, firstly, abductively formulate hypotheses on the behavior of real-world agents as cause for empirical realities (cf. Axelrod, 2007;Brenner and Werker, 2007). Agent-based models allow studying dynamics under ill-defined behavioral rules (heuristics) coping with uncertainty about the future (cf.…”

Adaptive workflow simulation of emergency response

“…The research methods' objective is twofold; first they are used to gather the necessary data for the development of the AWS in order to ground its development in emergency response practice. Grounding the development of the AWS simulation is quintessential to minimize the gap between reality and the simulation, will lead to a better founded simulation and increases the soundness of the results (Brenner & Werker, 2007; Auf der Heide, 2006;Turoff, Chummer, Van de Walle, & Yoa, 2004). Grounding here refers to the degree in which the assumptions and relations in a simulation are based on empirical findings instead of being hypothetical.…”

“…Simulation environments have been categorized based on: the degree in which they rely on empirical data instead of hypothetical assumptions and the generalizability of their results (Brenner & Werker, 2007); their theoretical basis (Crystal & Ellington, 2004); their application area, usage taxonomy, simulation taxonomy and design taxonomy (Sulistio et al, 2004). When applied to the use of simulation in the social sciences, Gilbert & Troitzsch (2005) point out that simulation types can be categorized using four characteristics: the number of levels that can be modelled in the simulation, the number of agents in a simulation, the complexity of the agents, and if communication between agents is possible or not.…”