Predicting Skills of Runaway Slaves in São Paulo, 1854-1887

Renato Colistete ()

No 2021_15, Working Papers, Department of Economics from University of São Paulo (FEA-USP)

Abstract: This paper examines the skills of enslaved labour during the second half of the nineteenth century in the province of São Paulo. The analysis is based on data from 3,376 individuals collected in advertisements of runaway slaves published by São Paulo newspapers between 1854 and 1887. As only a small part of the announcements listed runaways’ occupations, we draw on individual details on sex, age, ethnicity, residence, physical characteristics and other features of fugitives with advertised occupations to predict the skills of the remaining subset of runaways, using classification algorithms from machine learning. Overall, both observed and predicted skilled runaways converged in their characteristics: skilled runaways were mostly male, older than their low-skilled counterparts and predominantly from farms and plantations, rather than urban settings. Africans were not at a disadvantage in artisanal jobs when compared with Brazilian-born runaways, and the skill gap between mixed-race and black fugitives was negligible. Although the enslaved population suffered from very low levels of literacy, the few runaways with an ability to read or write tended to work in more qualified and artisanal occupations, indicating that education may have been valuable even under the appalling conditions of slavery. These results are important both for the analysis of slavery in Brazil and comparisons with other plantation societies in the Americas.

Keywords: Slavery; Runaways; Skills; Skilled slaves; Machine learning; São Paulo; Brazil (search for similar items in EconPapers)
JEL-codes: J24 N3 N36 N5 N56 (search for similar items in EconPapers)
Date: 2021-04-22, Revised 2021-04-23
New Economics Papers: this item is included in nep-his and nep-lma
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.repec.eae.fea.usp.br/documentos/Colistete_15WP.pdf (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:spa:wpaper:2021wpecon15

Ordering information: This working paper can be ordered from

Access Statistics for this paper

More papers in Working Papers, Department of Economics from University of São Paulo (FEA-USP) Contact information at EDIRC.
Bibliographic data for series maintained by Pedro Garcia Duarte ( this e-mail address is bad, please contact ).