EconBase
← All papers

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

Tiancheng Wang, Krishna Sharma

arXiv 2 Feb 2026 · Econometrics

arXiv:2602.02604 · PDF · DOI · OpenAlex · Extracted main text

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.

Citation extraction

33
references
55
in-text mentions
33
distinct cited
0
self-citations
6,680
main-text words

appendix boundary found by appendix_command · 55% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Giesecke, Oliver and Rauh, Joshua D (2022) How much do public employees value defined benefit versus defined contribution retirement benefits?1.00073100%
2Kargupta, Priyanka and Zhang, Nan and Zhang, Yunyi and Zhang, Rui an… (2025) TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora0.84333100%
3Campbell, Donald T and Fiske, Donald W (1959) Convergent and discriminant validation by the multitrait-multimethod matrix.0.73732100%
4Cronbach, Lee J and Meehl, Paul E (1955) Construct validity in psychological tests.0.73732100%
5Athey, Susan and Imbens, Guido W (2019) Machine learning methods that economists should know about0.64422100%
6Böke, Annkathrin and Hacker, Hannah and Chakraborty, Millennia and B… (2025) Observer-Independent Assessment of Content Overlap in Mental Health Questionnaires: Large Language Model–Based Study0.64422100%
7Borsboom, Denny and Mellenbergh, Gideon J and Van Heerden, Jaap (2004) The concept of validity.0.64422100%
8Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Du… (2018) Double/debiased machine learning for treatment and structural parameters0.64422100%
9Hommel, Björn E and Arslan, Ruben C (2025) Language models accurately infer correlations between psychological items and scales from text alone0.64422100%
10Huang, Zhen and Long, Yitian and Peng, Kaiping and Tong, Song (2025) An embedding-based semantic analysis approach: A preliminary study on redundancy detection in psychological concepts operational…0.64422100%

Showing the top 10 of 33 scored citations.