The Mixed Subjects Design: Treating Large Language Models as Potentially Informative Observations

David Broska, Michael Howes and Austin van Loon

Sociological Methods & Research, 2025, vol. 54, issue 3, 1074-1109

Abstract: Large language models (LLMs) provide cost-effective but possibly inaccurate predictions of human behavior. Despite growing evidence that predicted and observed behavior are often not interchangeable , there is limited guidance on using LLMs to obtain valid estimates of causal effects and other parameters. We argue that LLM predictions should be treated as potentially informative observations, while human subjects serve as a gold standard in a mixed subjects design . This paradigm preserves validity and offers more precise estimates at a lower cost than experiments relying exclusively on human subjects. We demonstrate—and extend—prediction-powered inference (PPI), a method that combines predictions and observations. We define the PPI correlation as a measure of interchangeability and derive the effective sample size for PPI. We also introduce a power analysis to optimally choose between informative but costly human subjects and less informative but cheap predictions of human behavior. Mixed subjects designs could enhance scientific productivity and reduce inequality in access to costly evidence.

Keywords: mixed subjects design; prediction-powered inference (PPI); PPI correlation; effective sample size; PPI poweranalysis; machine learning; large language models; computational social science (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/00491241251326865 (text/html)

Related works:
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:sae:somere:v:54:y:2025:i:3:p:1074-1109

DOI: 10.1177/00491241251326865

Access Statistics for this article

More articles in Sociological Methods & Research
Bibliographic data for series maintained by SAGE Publications ().