Detecting Causal Relationships in Simulation Models Using Intervention-based Counterfactual Analysis

Abstract

Central to explanatory simulation models is their capability to not just show that but also why particular things happen. Explanation is closely related with the detection of causal relationships and is, in a simulation context, typically done by means of controlled experiments. However, for complex simulation models, conventional “blackbox” experiments may be too coarse-grained to cope with spurious relationships. We present an intervention-based causal analysis methodology that exploits the manipulability of computational models, and detects and circumvents spurious effects. The core of the methodology is a formal model that maps basic causal assumptions to causal observations and allows for the identification of combinations of assumptions that have a negative impact on observability. First, experiments indicate that the methodology can successfully deal with notoriously tricky situations involving asymmetric and symmetric overdetermination and detect fine-grained causal relationships between events in the simulation. As illustrated in the article, the methodology can be easily integrated into an existing simulation environment.

Beyond Objects in Space-Time: Towards a Movement Analysis Framework with ‘How’ and ‘Why’ Elements

“…A few solutions have been proposed across a range of different disciplines to address some of these challenges. For example, Herd and Miles [55] present an intervention-based causal analysis model to explicate the complex causal mechanism within an agent-based simulation. Their automated approach is capable of examining and detecting causal connection between any given pair of events at a particular instant of time in ABMs.…”

“…Computer simulation has become a powerful tool in science for investigating complex real-world phenomena and conducting what-if analyses in an efficient way [55]. Similar to observational causal analysis, multiple simulation-based approaches can be implemented to model causal relations in different sciences: Microsimulation, Cellular Automata (CA), and ABM, being the most popular of these in the current context (see [56,57] for comparison and discussion).…”

Simulation Intelligence: Towards a New Generation of Scientific Methods

“…Simulation trace-based causality Given simulator execution traces in general consist of states, events, and actions, we can define causal relationships based on these entities -without this grounding, one cannot make reliable causal claims, which we discuss in the final example of this section. Herd & Miles [211] provide a practical formulation: event C causes event E in an actual trace π if and only if there exists a counterfactual trace π that is similar enough to π which requires that neither C nor E happens in the same state in which they happened in π. This suggests counterfactual analysis can be performed by searching all traces produced by the simulator for counterfactual π , but this is clearly intractable for any non-trivial simulator.…”

“…Simulation traces can be complex, amounting to several forms of causation based on the occurrence and omission of events in trace π [211]:…”

Report on Workshop: Planning the Future of Agent Simulation

“…On the first day of the workshop, participants presented their perspectives on the state of the art in simulation and simulation tools, introducing their existing work. On the application side, this included work using simulation in immunology (e.g., [1,7,11,13,15,17]), vascular biology (e.g., [4,5]), and synthetic biology [12], as well as in the social sciences [8] and, more generally, the evaluation of simulation results (e.g., [9,10]). Equally, Cosmo Tech, Slingshot Simulations, and the FLAME GPU Team presented on different approaches to high-performance simulation platforms that allow for domain specialization.…”