Novelty and Primacy: A Long-Term Estimator for Online Experiments

TL;DR

This paper introduces a difference-in-differences based observational method to estimate user-learning effects in online experiments, addressing the challenge of long-term impact assessment and improving decision-making in software development.

Contribution

It presents a novel approach for estimating user-learning at scale, demonstrating its advantages over traditional methods in ease of use and statistical power.

Findings

Effective estimation of user-learning at Microsoft experiments

Improved statistical power over existing methods

Limitations identified in presence of other treatment interactions

Abstract

Online experiments are the gold standard for evaluating impact on user experience and accelerating innovation in software. However, since experiments are typically limited in duration, observed treatment effects are not always permanently stable, sometimes revealing increasing or decreasing patterns over time. There are multiple causes for a treatment effect to change over time. In this paper, we focus on a particular cause, user-learning, which is primarily associated with novelty or primacy. Novelty describes the desire to use new technology that tends to diminish over time. Primacy describes the growing engagement with technology as a result of adoption of the innovation. User-learning estimation is critical because it holds experimentation responsible for trustworthiness, empowers organizations to make better decisions by providing a long-term view of expected impact, and prevents user dissatisfaction. In this paper, we propose an observational approach, based on difference-in-differences technique to estimate user-learning at scale. We use this approach to test and estimate user-learning in many experiments at Microsoft. We compare our approach with the existing experimental method to show its benefits in terms of ease of use and higher statistical power, and to discuss its limitation in presence of other forms of treatment interaction with time.