AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice

TL;DR

This paper introduces an iterative, LLM-based framework for extracting and refining economic measurements from survey data, improving understanding of behavioral factors in public employee pension choices.

Contribution

It presents a novel, flexible methodology that maps survey items to latent constructs, refines measurement taxonomy iteratively, and validates stability through out-of-sample tests.

Findings

Identifies semantic components with behavioral signals.

Clarifies economic mechanisms like beliefs versus constraints.

Provides a portable survey measurement audit.

Abstract

We develop an iterative framework for economic measurement that leverages large language models to extract measurement structure directly from survey instruments. The approach maps survey items to a sparse distribution over latent constructs through what we term a soft mapping, aggregates harmonized responses into respondent level sub dimension scores, and disciplines the resulting taxonomy through out of sample incremental validity tests and discriminant validity diagnostics. The framework explicitly integrates iteration into the measurement construction process. Overlap and redundancy diagnostics trigger targeted taxonomy refinement and constrained remapping, ensuring that added measurement flexibility is retained only when it delivers stable out of sample performance gains. Applied to a large scale public employee retirement plan survey, the framework identifies which semantic components contain behavioral signal and clarifies the economic mechanisms, such as beliefs versus constraints, that matter for retirement choices. The methodology provides a portable measurement audit of survey instruments that can guide both empirical analysis and survey design.