Randomization Inference in Two-Sided Market Experiments
By: Jizhou Liu, Azeem M. Shaikh, Panos Toulis
Potential Business Impact:
Tests online marketplaces fairly and accurately.
Randomized experiments are increasingly employed in two-sided markets, such as buyer-seller platforms, to evaluate treatment effects from marketplace interventions. These experiments must reflect the underlying two-sided market structure in their design (e.g., sellers and buyers), making them particularly challenging to analyze. In this paper, we propose a randomization inference framework to analyze outcomes from such two-sided experiments. Our approach is finite-sample valid under sharp null hypotheses for any test statistic and maintains asymptotic validity under weak null hypotheses through studentization. Moreover, we provide heuristic guidance for choosing among multiple valid randomization tests to enhance statistical power, which we demonstrate empirically. Finally, we demonstrate the performance of our methodology through a series of simulation studies.
Similar Papers
Robust Bayesian Inference of Causal Effects via Randomization Distributions
Methodology
Finds what truly causes changes in experiments.
Dependent Randomized Rounding for Budget Constrained Experimental Design
Machine Learning (Stat)
Helps poor countries test new ideas cheaply.
Causal Inference in Counterbalanced Within-Subjects Designs
Methodology
Fixes experiments where people try things one after another.