As public expectations for government performance rise with rapid technological progress, governments face growing pressure to design evidence-based policies that allocate resources efficiently and deliver customised services. Yet many existing evaluation tools are inadequate because they often ignore the fact that people respond differently to the same intervention. Instead, policy decisions typically rely on average effects, which can hide important variation - such as whether some people are harmed even when the average impact appears positive.

​

My ongoing research aims to improve how policies are evaluated by developing and applying a cutting-edge method that uncovers the entire distribution of treatment effects rather than just their average. Revealing this full range of responses allows us to identify who gains and who loses from a policy and to understand how interventions may affect economic inequality. This methodological innovation strengthens our ability to evaluate economic policies, enabling more precisely targeted interventions that enhance public well-being and reduce unnecessary public spending.

 

At the core of this research is a new method for identifying different parts (or “quantiles”) of the treatment-effect distribution under modest assumptions. This tool can address a wide range of policy-relevant questions: Does a welfare programme raise average income even if most participants are actually worse off and only a few benefit? Does an educational intervention that increases average test scores also widen inequality? What unintended consequences arise from an active labour market policy? How do alternative health insurance plans change the distribution of medical spending?

 

While my future research agenda will focus primarily on applications in economics, the method I develop has immediate relevance for other fields, including political science, sociology, psychology, biomedical science, and neuroscience. For example, the approach is well suited to biomedical data, where it can reveal the proportions of patients who benefit - or do not benefit - from a particular medical treatment.