Working Paper: CEPR ID: DP18186
Authors: Ran Spiegler
Abstract: When inferring the causal effect of one variable on another from correlational data, a common practice by professional researchers as well as lay decision makers is to control for some set of exogenous confounding variables. Choosing an inappropriate set of control variables can lead to erroneous causal inferences. This paper presents a model of lay decision makers who use long-run observational data to learn the causal effect of their actions on a payoff-relevant outcome. Different types of decision makers use different sets of control variables. I obtain upper bounds on the equilibrium welfare loss due to wrong causal inferences, for various families of data-generating processes. The bounds depend on the structure of the type space. When types are "ordered" in a certain sense, the equilibrium condition greatly reduces the cost of wrong causal inference due to poor controls.
Keywords: worst-case analysis
JEL Codes: D91
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| failing to control for relevant exogenous variables (C20) | biased estimates of causal effects (C51) |
| correctly controlling for all relevant exogenous variables (C51) | accurate estimates of causal effects (C51) |
| not controlling for a confounding variable (x) (C29) | erroneous non-zero effect perceived (C92) |
| correctly controlling for variables (C39) | minimize welfare loss (D69) |
| structure of the type space and types' control variables (C69) | influence the extent of causal inference errors (C20) |