EconPapers    
Economics at your fingertips  
 

Inequality of Opportunity in Education in Spanish Regions: A Machine Learning Approach

Pablo Bencomo-Mesa, Gustavo A. Marrero and Gabriela Sicilia
Additional contact information
Pablo Bencomo-Mesa: Universidad de La Laguna
Gustavo A. Marrero: Universidad de La Laguna and EQUALITAS
Gabriela Sicilia: Universidad Autónoma de Barcelona

Hacienda Pública Española / Review of Public Economics, 2025, vol. 252, issue 1, 113-162

Abstract: Inequality of Opportunity in Achievement (IOpE) measures the importance of factors beyond the student’s control in explaining differences in academic performance. Using PISA 2018, we estimate the IOpE for Spanish regions using conditional inference tree (CIT) and forest (CIF). Using CIFs, IOpE is twice as high as those obtained using traditional approaches (on average, 43% compared to 20%). Murcia and Extremadura are among those with the highest IOpE, while Castilla-La Mancha and the Pais Vasco have the lowest IOpE. The circumstances that contribute most to IOpE are the cultural environment at home (number of books) and parental occupation.

Keywords: Inequality of opportunity; Academic achievement; Machine learning; PISA; Spanish regions (search for similar items in EconPapers)
JEL-codes: D63 I24 I28 O52 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hpe-rpe.org/wp-admin/admin-ajax.php?juwpfi ... b8dfad6df8&preview=1 (application/pdf)

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:hpe:journl:y:2025:v:252:i:1:p:113-162

Access Statistics for this article

More articles in Hacienda Pública Española / Review of Public Economics from IEF Contact information at EDIRC.
Bibliographic data for series maintained by Miguel Gómez de Antonio ().

 
Page updated 2025-03-27
Handle: RePEc:hpe:journl:y:2025:v:252:i:1:p:113-162