Policy Determinants of School Outcomes Under Model Uncertainty: Evidence from South Africa

Thomas Laurent, Fabrice Murtin, Geoff Barnard (), Dean Janse van Rensburg, Vijay Reddy, George Frempong and Lolita Winnaar
Additional contact information
Thomas Laurent: Institut national de la statistique et des études économiques
Dean Janse van Rensburg: Human Sciences Research Council
Vijay Reddy: Human Sciences Research Council
George Frempong: Human Sciences Research Council
Lolita Winnaar: Human Sciences Research Council

No 1057, OECD Economics Department Working Papers from OECD Publishing

Abstract: In this paper we assess the determinants of secondary school outcomes in South Africa. We use Bayesian Averaging Model techniques to account for uncertainty in the set of underlying factors that are chosen among a very large pool of explanatory variables in order to minimize the risk of omitted variable bias. Our analysis indicates that the socioeconomic background of pupils, demographic characteristics such as population groups (Black and White) as well as geographical locations account for a significant variation in pupils’ achievement levels. We also find that the most robust policy determinants of pupils’ test scores are the availability of a library at school, the use of IT in the classroom as well as school climate. This Working Paper relates to the 2013 OECD Economic Survey of South Africa (http://www.oecd.org/eco/surveys/southafrica2013.htm).

Les politiques d'éducation face à l'incertitude de la modélisation : l'Afrique du Sud à l'étude Cette étude estime les déterminants des résultats scolaires en Afrique du Sud. Des techniques Bayésiennes de sélection de modèle sont utilisées pour traiter l’incertitude dans le choix des variables explicatives, lesquelles sont tirées d’un ensemble très large de variables candidates aidant à minimiser le biais d’omission. Les résultats indiquent que le profil socio-économique des élèves, les caractéristiques démographiques telles que l’appartenance ethnique ou la localisation géographique expliquent une partie importante des différences de performance scolaire entre élèves. Les politiques éducatives corrélées aux résultats scolaires sont la disponibilité de bibliothèques à l’école, l’utilisation des technologies de l’information en classe ainsi que la discipline à l’école. Ce Document de travail se rapporte à l'Étude économique de l’Afrique du Sud, 2013, (http://www.oecd.org/fr/eco/etudes/afriquedusud2013.htm).

Keywords: Afrique du Sud; Bayesian model averaging; choix de modèles par estimateur Bayésien; education; South Africa; éducation (search for similar items in EconPapers)
JEL-codes: C2 H4 I2 O2 (search for similar items in EconPapers)
Date: 2013-06-06
New Economics Papers: this item is included in nep-afr and nep-edu
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1787/5k452klln7tl-en (text/html)

Related works:
Journal Article: Policy Determinants of School Outcomes under Model Uncertainty: Evidence from South Africa (2015)
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:oec:ecoaaa:1057-en

Access Statistics for this paper

More papers in OECD Economics Department Working Papers from OECD Publishing Contact information at EDIRC.
Bibliographic data for series maintained by ().