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

• URL: http://arxiv.org/abs/2602.02604v1
• Date: Mon, 02 Feb 2026 02:22:36 GMT
• Title: AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice
• Abstract summary: We develop an iterative framework for economic measurement that leverages large language models to extract measurement structure directly from survey instruments.<n>The framework is applied to a large scale public employee retirement plan survey.
• Score: 2.2324302196460706
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application [3.4545547482062378]
  AICOME is a framework for evaluating whether AI-derived respondent-level measures can recover individual and group-level effects in contextual models.<n>We validate the framework using the 2022 China Family Panel Studies (CFPS), where occupations provide the empirical grouping structure.<n>Results show that AI contextual measurement can recover much of the contextual-model information contained in observed survey variables when rich respondent and job characteristics are available.
  arXiv  Detail & Related papers  (2026-09-02T17:09:30Z)
• From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research [0.0]
  Structural equation modelling (SEM) is widely used in survey-based business and information systems research.<n>This study develops and demonstrates a staged robustness analysis framework that connects SEM, ordinary least squares (OLS) regression, and Double Machine Learning (DML)<n>The findings identify which relationships are stable across SEM, OLS, and DML-style checks, and which require more cautious interpretation.
  arXiv  Detail & Related papers  (2026-07-01T06:46:33Z)
• Pitfalls in Evaluating Interpretability Agents [91.49742416116635]
  We build an agentic system in which a research agent iteratively designs experiments and refines hypotheses.<n>Our work demonstrates fundamental challenges in evaluating complex automated interpretability systems.
  arXiv  Detail & Related papers  (2026-03-20T16:27:17Z)
• Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity [66.94391219005291]
  This paper proposes Agentic Cognitive Profiling (ACP), an agentic framework that realigns automated screening with clinical protocol logic.<n>Central to our design is decoupling semantic understanding from measurement by delegating all quantification to deterministic function calling.<n>ACP achieves 90.5% score match rate in task examination and 85.3% accuracy in AD prediction, surpassing popular baselines.
  arXiv  Detail & Related papers  (2026-03-18T06:15:35Z)
• Discovering Semantic Latent Structures in Psychological Scales: A Response-Free Pathway to Efficient Simplification [7.405170407676887]
  We introduce a topic-modeling framework that operationalizes semantic latent structure for scale simplification.<n>Items are encoded using contextual sentence embeddings and grouped via density-based clustering.<n>We benchmarked the framework across DASS, IPIP, and EPOCH, evaluating structural recovery, internal consistency, factor congruence, correlation preservation, and reduction efficiency.
  arXiv  Detail & Related papers  (2026-02-13T03:37:15Z)
• Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models [122.58252919699122]
  Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the decision-making of Large Language Models (LLMs)<n>We present a practical survey structured around the pipeline: "Awesomeinterventionable-MI-Survey"
  arXiv  Detail & Related papers  (2026-01-20T14:23:23Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• An Investigation on How AI-Generated Responses Affect SoftwareEngineering Surveys [3.183470571353323]
  This study explores how large language models (LLMs) are being misused in software engineering surveys.<n>We analyzed data from two survey deployments conducted in 2025 through the Prolific platform.<n>We identify data authenticity as an emerging dimension of validity in software engineering surveys.
  arXiv  Detail & Related papers  (2025-12-19T11:17:05Z)
• The Software Infrastructure Attitude Scale (SIAS): A Questionnaire Instrument for Measuring Professionals' Attitudes Toward Technical and Sociotechnical Infrastructure [10.916181267471098]
  Recent software engineering (SE) research has highlighted the need for sociotechnical research, implying a demand for customized psychometric scales.<n>We define the concepts of technical and sociotechnical infrastructure in software engineering, and develop and validate a psychometric scale that measures attitudes toward them.
  arXiv  Detail & Related papers  (2025-11-30T12:03:21Z)
• Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach [2.162862183067095]
  Social scientists are increasingly turning to unstructured datasets to unlock new empirical insights.<n>This paper proposes a general and flexible framework for pursuing discovery from unstructured data in a statistically principled way.<n>An open source Jupyter notebook is provided for researchers to implement the framework in their own projects.
  arXiv  Detail & Related papers  (2025-11-03T15:42:32Z)
• Modeling User Behavior from Adaptive Surveys with Supplemental Context [1.433758865948252]
  We present LANTERN, a modular architecture for modeling user behavior by fusing adaptive survey responses with contextual signals.<n>We demonstrate the architectural value of maintaining survey primacy through selective gating, residual connections and late fusion.<n>We further investigate threshold sensitivity and the benefits of selective modality reliance through ablation and rare/frequent attribute analysis.
  arXiv  Detail & Related papers  (2025-07-28T15:19:54Z)
• A validity-guided workflow for robust large language model research in psychology [0.0]
  Large language models (LLMs) are rapidly being integrated into psychological research as research tools, evaluation targets, human simulators, and cognitive models.<n>These "measurement phantoms"--statistical artifacts masquerading as psychological phenomena--threaten the validity of a growing body of research.<n>Guided by the dual-validity framework that integrates psychometrics with causal inference, we present a six-stage workflow that scales validity requirements to research ambition.
  arXiv  Detail & Related papers  (2025-07-06T18:06:12Z)
• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective.<n>The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning.<n>The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Variable Importance Matching for Causal Inference [73.25504313552516]
  We describe a general framework called Model-to-Match that achieves these goals. Model-to-Match uses variable importance measurements to construct a distance metric. We operationalize the Model-to-Match framework with LASSO.
  arXiv  Detail & Related papers  (2023-02-23T00:43:03Z)
• ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning [63.77667876176978]
  Large language models show improved downstream task interpretability when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively studying their correctness is difficult. We present ROS, a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics.
  arXiv  Detail & Related papers  (2022-12-15T15:52:39Z)
• Foreseeing the Benefits of Incidental Supervision [83.08441990812636]
  This paper studies whether we can, in a single framework, quantify the benefits of various types of incidental signals for a given target task without going through experiments. We propose a unified PAC-Bayesian motivated informativeness measure, PABI, that characterizes the uncertainty reduction provided by incidental supervision signals.
  arXiv  Detail & Related papers  (2020-06-09T20:59:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.