NBER Working Papers · October 27, 2026 · On the brief until November 10, 2026

An LLM Workflow for Functional Form Sensitivity Analysis -- by Isaiah Andrews, Simon C. Essig Aberg, Jesse M. Shapiro

EconomicsData Science

THE AI ANGLE

Running workflows to test functional form sensitivity

Researchers developed a large language model workflow to test functional form sensitivity in empirical estimation. The tool searches for analytic solutions or uses constrained numerical methods to establish a verifiable lower bound on sensitivity. This process gives practitioners a fast way to check if alternative functional forms that match data fit alter their main estimates.

Summary written by AI Business Lens with an AI model from the article at nber.org. It is not the article, and the publisher has not reviewed it. For publishers.

THE TEACHING ANGLE

Classes can examine whether an empirical finding holds value if alternative functional forms fit the data equally well yet change the target estimate.

Read the original at nber.org Generate teaching or study materials

Instructors get discussion guides, assignments, and mini-cases. Students and readers get a plain summary, points to raise, an exercise, and a self-check. All built from the full article. A free account saves stories and gives you three generations. Stories stay on the brief for 14 days. After that this page keeps the link to the original.

An LLM Workflow for Functional Form Sensitivity Analysis -- by Isaiah Andrews, Simon C. Essig Aberg, Jesse M. Shapiro

More in Economics