Modelos de Resposta para Experimentos Randomizados em Redes Sociais de Larga Escala

TL;DR

This paper introduces a new response model for randomized experiments on large-scale social networks, analyzes theoretical estimation limits, and evaluates model misspecification effects through empirical results.

Contribution

It proposes a novel response model, derives theoretical bounds for estimation errors, and assesses the impact of model misspecification in social network experiments.

Findings

New response model for social network experiments

Theoretical limits for estimation error derived

Empirical analysis of model misspecification effects

Abstract

A/B tests are randomized experiments frequently used by companies that offer services on the Web for assessing the impact of new features. During an experiment, each user is randomly redirected to one of two versions of the website, called treatments. Several response models were proposed to describe the behavior of a user in a social network website, where the treatment assigned to her neighbors must be taken into account. However, there is no consensus as to which model should be applied to a given dataset. In this work, we propose a new response model, derive theoretical limits for the estimation error of several models, and obtain empirical results for cases where the response model was misspecified.