Statistical inference of long-term causal effects in multiagent systems under the Neyman-Rubin model. (arXiv:1501.02315v1 [stat.ME])

Estimation of causal effects of interventions in dynamical systems of interacting agents is under-developed. In this paper, we explore the intricacies of this problem through standard approaches, and demonstrate the need for more appropriate methods. Working under the Neyman-Rubin causal model, we proceed to develop a causal inference method and we explicate the stability assumptions that are necessary for valid causal inference. Our method consists of a behavioral component that models the evolution of agent behaviors over time and informs on the long-term distribution of agent behaviors in the system, and a game-theoretic component that models the observed distribution of agent actions conditional on adopted behaviors. This allows the imputation of long-term estimates of quantities of interest, and thus the estimation of long-term causal effects of interventions. We demonstrate our method on a dataset from behavioral game theory, and discuss open problems to stimulate future research.

from cs.AI updates on arXiv.org http://ift.tt/1AK82il

via IFTTT