Qiang Chen, Tianyang Han, Jin Li, Ye Luo, Yuxiao Wu, Xiaowei Zhang, Tuo Zhou
arXiv 1 Jun 2025 · Econometrics
arXiv:2506.00856 · PDF · DOI · OpenAlex · Extracted main text
Can AI effectively perform complex econometric analysis traditionally requiring human expertise? This paper evaluates AI agents' capability to master econometrics, focusing on empirical analysis performance. We develop an “Econometrics AI Agent” built on the open-source MetaGPT framework. This agent exhibits outstanding performance in: (1) planning econometric tasks strategically, (2) generating and executing code, (3) employing error-based reflection for improved robustness, and (4) allowing iterative refinement through multi-round conversations. We construct two datasets from academic coursework materials and published research papers to evaluate performance against real-world challenges. Comparative testing shows our domain-specialized AI agent significantly outperforms both benchmark large language models (LLMs) and general-purpose AI agents. This work establishes a testbed for exploring AI's impact on social science research and enables cost-effective integration of domain expertise, making advanced econometric methods accessible to users with minimal coding skills. Furthermore, our AI agent enhances research reproducibility and offers promising pedagogical applications for econometrics teaching.
appendix boundary found by appendix_command · 97% 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 | Hong, Sirui, Lin, Yizhang, Liu, Bang, Liu, Bangbang, Wu, Binhao, Zha… (2024) Data Interpreter: An LLM Agent For Data Science self | 0.644 | 2 | 2 | 100% |
| 2 | Almond, D., Chay, K.Y., Lee, D.S (2005) The Costs of Low Birth Weight | 0.511 | 2 | 1 | 100% |
| 3 | Abraham, J., Olbert, M., Vasvari, F (2024) ESG Disclosures in the Private Equity Industry | 0.405 | 1 | 1 | 100% |
| 4 | Ahrens, Maximilian, Erdemlioglu, Deniz, McMahon, Michael, Neely, Chr… (2025) Mind your language: Market responses to central bank speeches | 0.405 | 1 | 1 | 100% |
| 5 | Anderson, Michael (2008) Safety for whom? The effects of light trucks on traffic fatalities | 0.405 | 1 | 1 | 100% |
| 6 | Armstrong, Daphne M., Glaeser, Stephen, Hoopes, Jeffrey L (2024) Measuring firm exposure to government agencies | 0.405 | 1 | 1 | 100% |
| 7 | Balsmeier, Benjamin, Fleming, Lee, Stiebale, Joel, Veihl, Maria (2024) The Unintended Impact of R&D Tax Credits on Innovative Search | 0.405 | 1 | 1 | 100% |
| 8 | Brynjolfsson, Erik, Li, Danielle, Raymond, Lindsey (2025) Generative AI at Work | 0.405 | 1 | 1 | 100% |
| 9 | Bursztyn, Leonardo, Rao, Aakaash, Roth, Christopher, Yanagizawa-Drot… (2022) Opinions as Facts | 0.405 | 1 | 1 | 100% |
| 10 | Card, D., Sullivan, D (1988) Measuring the Effect of Subsidized Training Programs on Movements In and Out of Employment | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 51 scored citations.