Combining decision-level data from multiple experiments: what is the pooled estimator doing?
Abstract
Abstract When analyzing decision-level data from more than one economic experiment, the pooled ordinary least squares (OLS) estimator is a weighted sum of (i) within-experiment treatment effects, and (ii) an estimate of between-experiment treatment effects. The latter is plausibly biased and receives substantial weight in typical studies. I discuss some implications of this weighting and some remedies to the problem.
Fields of Study & Subjects
Economic and Environmental Valuation
Decision-Making and Behavioral Economics
Advanced Causal Inference Techniques
Publication details
- Journal / source
- Journal of the Economic Science Association
- Publisher
- Cambridge University Press (CUP)
- Pages
- 1–13
- Publication date
- 22 April 2026
- Language
- EN