AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice
This provides a portable measurement audit tool for economists and survey designers to improve empirical analysis and survey design, though it is incremental as it builds on existing methods with new integration and validation steps.
The authors tackled the problem of extracting economic measurement structure from survey instruments by developing an iterative framework that uses large language models to map survey items to latent constructs and validate the taxonomy through out-of-sample tests. The result is a method that identifies semantic components with behavioral signal and clarifies economic mechanisms like beliefs versus constraints for retirement choices, as demonstrated on a public employee pension survey.
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.