AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912870742097920 |
|---|---|
| author | Wang, Tiancheng Sharma, Krishna |
| author_facet | Wang, Tiancheng Sharma, Krishna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02604 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice Wang, Tiancheng Sharma, Krishna Econometrics Artificial Intelligence 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. |
| title | AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice |
| topic | Econometrics Artificial Intelligence |
| url | https://arxiv.org/abs/2602.02604 |