SearcharxivSearch

arXiv subjects

Evgeni Drynkin

Publications and source records attributed to Evgeni Drynkin.

2 recordsLinked to original sources

Causal inference with bipartite designs: A generalized propensity score approach

Bipartite experiments, in which one set of units receives a treatment while outcomes are measured on another set, have recently garnered attention for their ability to capture interference across two distinct populations, such as buyers and sellers in online marketplaces. However, analyzing these experiments can be challenging, given that exposure is neither purely binary nor independent across units. In this paper, we propose a unified framework for causal inference in bipartite designs that leverages generalized propensity scores (GPS) to estimate exposure-response functions. Under standard unconfoundedness assumptions, we show that our GPS-based estimators are unbiased and derive theoretical bounds on their variance. We further introduce practical modeling and weighting strategies, along with double deconfounding methods, that integrate the GPS into both the outcome model and the assignment mechanism. Through extensive simulations, we demonstrate that these approaches achieve substantial bias reduction compared to naive methods. We also illustrate their effectiveness in a real-world application using an Amazon Pet Supplies dataset, where controlling for network structure proves critical to drawing valid causal conclusions. Our results underscore the importance of bipartite designs in contexts with significant interference and highlight how GPS-based methods can bolster the reliability of causal effect estimates in such settings.

stat.ME

Estimation of Discrete Choice Models: A Machine Learning Approach

In this paper we propose a new method of estimation for discrete choice demand models when individual level data are available. The method employs a two-step procedure. Step 1 predicts the choice probabilities as functions of the observed individual level characteristics. Step 2 estimates the structural parameters of the model using the estimated choice probabilities at a particular point of interest and the moment restrictions. In essence, the method uses nonparametric approximation (followed by) moment estimation. Hence the name---NAME. We use simulations to compare the performance of NAME with the standard methodology. We find that our method improves precision as well as convergence time. We supplement the analysis by providing the large sample properties of the proposed estimator.

stat.AP