Working Paper: CEPR ID: DP10062
Authors: Ran Spiegler
Abstract: I present a framework for analyzing decision makers with an imperfect understanding of their environment's correlation structure. The decision maker faces an objective multivariate probability distribution (his own action is one of the random variables). He is characterized by a directed acyclic graph over the set of variables. His subjective belief filters the objective distribution through his graph, via the factorization formula for Bayesian networks. This belief distortion implies that the decision maker's long-run behavior may affect his perception of the consequences of his actions. Accordingly, I define a "personal equilibrium" notion of optimal choices. I show how recent models of boundedly rational expectations (as well as new ones, e.g. reverse causality) can be subsumed into this framework as special cases. Some general properties of the Bayesian-network representation of subjective beliefs are presented, as well as a "missing data" foundation.
Keywords: Bayesian networks; Boundedly rational expectations; Coarse reasoning; Directed acyclic graphs; Misspecified models; Personal equilibrium; Reverse causality
JEL Codes: D03
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| DM's subjective belief system (D91) | distorts objective probability distribution (C46) |
| distorts objective probability distribution (C46) | misperception of the correlation structure among variables (C10) |
| misperception of the correlation structure among variables (C10) | suboptimal decisions (D91) |
| DM's actions (Y60) | affects belief about consequences of actions (D91) |
| misperception of causal link between health and chemical levels (I12) | takes medication despite adverse effects (I12) |
| reverse causality (C22) | erroneous conclusions about relationship between actions and outcomes (D91) |