nep-lam 2026-05-25 papers

on Central and South America

Issue of 2026–05–25
two papers chosen by
Maximo Rossi, Universidad de la RepÃÃººblica

Deep Research on a Loop: Using AI Agents to Construct Economic Datasets By Santiago Afonso; Sebastian Galiani; Ramiro H. Gálvez; Raul A. Sosa
Intergenerational mobility in Uruguay using income-tax administrative data By Martín Leites; Xavier Ramos; Cecilia Rodríguez; Joan Vilá

Deep Research on a Loop: Using AI Agents to Construct Economic Datasets

By:	Santiago Afonso; Sebastian Galiani; Ramiro H. Gálvez; Raul A. Sosa
Abstract:	Constructing datasets from primary sources is one of the costliest tasks in empirical economics. We propose Deep Research on a Loop (DRIL), a methodology that uses AI agents to assemble datasets from publicly available sources. DRIL applies a fixed research instrument across a mapped unit space (e.g., countries by years), with a two-stage architecture separating design from implementation. The instrument specifies variables and coding rules, an evidence policy governs sources and citations, and data quality mechanisms track gaps and uncertainty explicitly. We exercise DRIL on a 2025 update of the Global Tax Expenditures Database for eight Latin American and Caribbean countries. The run produces 129 sources and 136 evidence records, covering 22 qualitative fields fully and 6 quantitative estimate types with documented gaps, at the cost of a standard LLM subscription comparable to a few hours of research-assistant work. We argue that even partial automation of dataset construction can shift the production function of empirical economics.
JEL:	C0
Date:	2026–05
URL:	https://d.repec.org/n?u=RePEc:nbr:nberwo:35188

Intergenerational mobility in Uruguay using income-tax administrative data

By:	Martín Leites (IECON-UDELAR, Uruguay and EQUALITAS.); Xavier Ramos (Department of Applied Economics, Universitat Autònoma de Barcelona, Spain; IZA and EQUALITAS.); Cecilia Rodríguez (IECON-UDELAR, Uruguay.); Joan Vilá (IECON-UDELAR, Uruguay.)
Abstract:	We contribute to the very incipient literature that estimates the intergenerational mobility of income from large-scale administrative data using high-quality income data and provide novel evidence of intergenerational income mobility in a middle-income country, Uruguay. Our estimates address the important role of informal labor markets, one of the features of low- and middle-income countries, and a major challenge to obtain unbiased estimates of intergenerational mobility in these countries. We estimate an IRA of 0.292, indicating that persistence is higher in Uruguay than in high-income countries, but lower than in the US. Our results show that (i) informal income increases intergenerational persistence, (ii) intergenerational persistence is higher at the upper half of the distribution, especially at the richest decile, and (iii) intergenerational income persistence is largest among parents and children of the same sex.
Keywords:	Intergenerational income mobility, Informal labor markets, Uruguay.
Date:	2026–05
URL:	https://d.repec.org/n?u=RePEc:uab:wprdea:wpdea2603

This nep-lam issue is ©2026 by Maximo Rossi. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.

General information on the NEP project can be found at https://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.

NEP’s infrastructure is sponsored by the Griffith Business School of Griffith University in Australia.