Advancement to Candidacy Presentation:“Obtaining Single-Shot Causal Effects in Time-Varying Treatment Settings: An Application to the Regional Impacts of a Small Business Lending Program”, Spencer Sween, PhD Student, UCSB
Speaker
Spencer Sween, PhD Student, UC Santa Barbara
Biography
Spencer Sween is a Ph.D. student in Economics at the University of California, Santa Barbara, where he also received his Bachelor of Arts and Master’s degrees in Economics. His research interests lie in applied econometrics, causal machine learning, and the economic effects of financial access. His current work focuses on integrating machine learning methods with panel-data techniques, such as difference-in-differences, to study non-standard treatment regimes. On the applied side, he examines how federal credit access policies affect local labor markets and entrepreneurship rates in underserved communities. Outside of research, he serves as the Head Teaching Assistant for Introduction to Econometrics at UCSB. When not in the office, he can often be found on a tennis or pickleball court.
Event Details
Spencer will be presenting his Advancement to Candidacy paper, “Obtaining Single-Shot Causal Effects in Time- Varying Treatment Settings: An Application to the Regional Impacts of a Small Business Lending Program”. To access the Advancement paper, you must have an active UCSB NetID and password.
Abstract
This paper develops an econometric framework to isolate the incremental effects of a single treatment intervention in settings where continuously measured policies are implemented repeatedly over time. Traditional difference-in-differences methods aggregate causal responses across the entire treatment path, potentially obscuring the ability to precisely quantify and interpret policy effects arising from a marginal increase in treatment exposure. To address this, we introduce a “single-shot” treatment effect parameter, which captures the average intertemporal response to the first non-zero treatment increment. We establish semi-parametric identification results and propose new estimators that flexibly integrate machine learning techniques to control for high-dimensional covariates. Applying our methodology to the U.S. Small Business Administration’s 504 program—a policy that subsidizes financing for large capital investment projects to spur regional economic development—we find that a single guaranteed 504 project increases local employment by approximately 1.1% over five years, with no significant effect on wages. Our results reveal substantial local employment multipliers in the manufacturing sector that conventional methods understate.
JEL Codes: C14, C23, G21, H81, R11