Inference for Regression with Variables Generated by AI or Machine Learning

Laura Battaglia, Tim Christensen, Stephen Hansen and Szymon Sacher

No 19115, CEPR Discussion Papers from Centre for Economic Policy Research

Abstract: It has become common practice for researchers to use AI-powered information retrieval algorithms or other machine learning methods to estimate variables of economic interest, then use these estimates as covariates in a regression model. We show both theoretically and empirically that naively treating AI- and ML-generated variables as “data†leads to biased estimates and invalid inference. We propose two methods to correct bias and perform valid inference: (i) an explicit bias correction with bias-corrected confidence intervals, and (ii) joint maximum likelihood estimation of the regression model and the variables of interest. Through several applications, we demonstrate that the common approach generates substantial bias, while both corrections perform well.

Keywords: Measurement error; Artificial intelligence; Large Language Models; Topic models; Joint inference (search for similar items in EconPapers)
JEL-codes: C11 C51 C55 (search for similar items in EconPapers)
Date: 2024-05
References: Add references at CitEc
Citations:

Downloads: (external link)
https://cepr.org/publications/DP19115 (application/pdf)

Related works:
Working Paper: Inference for Regression with Variables Generated by AI or Machine Learning (2025)
Working Paper: Inference for Regression with Variables Generated by AI or Machine Learning (2025)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cpr:ceprdp:19115

Ordering information: This working paper can be ordered from
https://cepr.org/publications/DP19115

Access Statistics for this paper

More papers in CEPR Discussion Papers from Centre for Economic Policy Research 33 Great Sutton Street, London EC1V 0DX, UK.
Bibliographic data for series maintained by CEPR ().