arXiv 21 Sep 2024 · Econometrics · 5 citations (OpenAlex)
arXiv:2409.14202 · PDF · DOI · OpenAlex · Extracted main text
The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process, and justifying its validity -- especially exclusion restrictions -- is largely rhetorical. We propose using large language models (LLMs) to search for new IVs through narratives and counterfactual reasoning, similar to how a human researcher would. The stark difference, however, is that LLMs can dramatically accelerate this process and explore an extremely large search space. We demonstrate how to construct prompts to search for potentially valid IVs. We contend that multi-step and role-playing prompting strategies are effective for simulating the endogenous decision-making processes of economic agents and for navigating language models through the realm of real-world scenarios, rather than anchoring them within the narrow realm of academic discourses on IVs. We apply our method to three well-known examples in economics: returns to schooling, supply and demand, and peer effects. We then extend our strategy to finding (i) control variables in regression and difference-in-differences and (ii) running variables in regression discontinuity designs.
appendix boundary found by appendix_command · 92% of the source is main text. Read the extracted text to check this.
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.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Imbens, G. W. and J. D. Angrist (1994) Identification and Estimation of Local Average Treatment Effects | 0.843 | 3 | 3 | 100% |
| 2 | Ludwig, J. and S. Mullainathan (2024) Machine Learning as a Tool for Hypothesis Generation | 0.737 | 3 | 2 | 100% |
| 3 | Angrist, J. D., K. Graddy, and G. W. Imbens (2000) The Interpretation of Instrumental Variables Estimators in Simultaneous Equations Models with an Application to the Demand for F… | 0.644 | 4 | 1 | 100% |
| 4 | Du, T., A. Kanodia, H. Brunborg, K. Vafa, and S. Athey (2024) LABOR-LLM: Language-Based Occupational Representations with Large Language Models | 0.644 | 2 | 2 | 100% |
| 5 | Heckman, J. J. and E. Vytlacil (2005) Structural Equations, Treatment Effects, and Econometric Policy Evaluation1 | 0.644 | 2 | 2 | 100% |
| 6 | Pearl, J (2000) Causality: Models, Reasoning, and Inference | 0.644 | 2 | 2 | 100% |
| 7 | Card, D. and A. B. Krueger (1994) Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania | 0.511 | 2 | 2 | 50% |
| 8 | Ackerberg, D. A., K. Caves, and G. Frazer (2015) Identification Properties of Recent Production Function Estimators | 0.511 | 2 | 1 | 100% |
| 9 | Card, D (1995) Using Geographic Variation in College Proximity to Estimate the Return to Schooling, in | 0.511 | 2 | 1 | 100% |
| 10 | Card, D (2001) Estimating the return to schooling: Progress on some persistent econometric problems | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 57 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.