Economic inferences using language models

Mittendorf, Daniel (2025) Economic inferences using language models. PhD thesis, University of Glasgow.

Abstract

I consider how causal and predictive economic inference problems can be solved using textual data. In doing so, I particularly investigate opportunities created by recent advances in natural language modelling, which appear to remain underexplored as an econometric methodology—a gap this thesis aims to help fill. Through this lens, I revisit three economic inference problems: estimation of the dynamic causal effects of monetary policy, forecasting of macroeconomic aggregates, and predicting financial risk premia. Re-examining the dynamic causal effects of UK monetary policy, I find that orthogonalising conventional instrumental variables with respect to large language model-extracted information appears to help resolve longstanding puzzles within empirical monetary economics. Examining the incremental value of the text of the Federal Reserve System’s ‘Beige Book’ for forecasting US macroeconomic aggregates, I find apparent improvements in forecast accuracy, but also show how the inclusion of language model-generated predictors can make bias-free forecast evaluation challenging. Considering an investor’s inference problem, I make a formal connection between microeconomic theory regarding rankings of information structures and the practical choice of which words or tokens should be prioritised in financial language modelling. Taken together, these findings underscore that language models are a powerful addition to the econometric instrumentarium available to researchers and practitioners. Whilst there are pitfalls to avoid, there can be little doubt that language models will become essential tools for drawing economic inferences.

• Item Type: Thesis (PhD)
• Qualification Level: Doctoral
• Additional Information: This work was supported by the Economic and Social Research Council (ESRC) [project reference 2448498].
• Subjects: H Social Sciences > HB Economic Theory
• Colleges/Schools: College of Social Sciences > Adam Smith Business School > Economics
• Funder's Name: Economic and Social Research Council (ESRC)
• Supervisor's Name: Korobilis, Professor Dimitris and Chen, Professor Cathy Yi-Hsuan
• Date of Award: 2025
• Depositing User: Theses Team
• Unique ID: glathesis:2025-85360
• Copyright: Copyright of this thesis is held by the author.
• Date Deposited: 15 Aug 2025 08:12
• Last Modified: 15 Aug 2025 08:15
• Thesis DOI: 10.5525/gla.thesis.85360
• URI: https://theses.gla.ac.uk/id/eprint/85360