1. Causal inference with misspecified exposure mappings: separating definitions and assumptions
- Author
-
Fredrik Sävje
- Subjects
FOS: Computer and information sciences ,Statistics and Probability ,Applied Mathematics ,General Mathematics ,Econometrics (econ.EM) ,Mathematics - Statistics Theory ,Statistics Theory (math.ST) ,Agricultural and Biological Sciences (miscellaneous) ,Methodology (stat.ME) ,FOS: Economics and business ,FOS: Mathematics ,Statistics, Probability and Uncertainty ,General Agricultural and Biological Sciences ,Statistics - Methodology ,Economics - Econometrics - Abstract
Summary Exposure mappings facilitate investigations of complex causal effects when units interact in experiments. Current methods require experimenters to use the same exposure mappings to define the effect of interest and to impose assumptions on the interference structure. However, the two roles rarely coincide in practice, and experimenters are forced to make the often questionable assumption that their exposures are correctly specified. This paper argues that the two roles exposure mappings currently serve can, and typically should, be separated, so that exposures are used to define effects without necessarily assuming that they are capturing the complete causal structure in the experiment. The paper shows that this approach is practically viable by providing conditions under which exposure effects can be precisely estimated when the exposures are misspecified. Some important questions remain open.
- Published
- 2023