The Added Value of More Accurate Predictions for School Rankings

26 Pages Posted: 6 Aug 2019

See all articles by Paolo Sestito

Paolo Sestito

Bank of Italy

Fritz Schiltz

University of Leuven

Tommaso Agasisti

Politecnico di Milano - Department of Management, Economics and Industrial Engineering

K. De Witte

University of Leuven (KUL); Maastricht University

Date Written: February 4, 2019

Abstract

School rankings based on value-added (VA) estimates are subject to prediction errors, since VA is defined as the difference between predicted and actual performance. We introduce a more flexible random forest (RF), rooted in the machine learning literature, to minimize prediction errors and to improve school rankings. Monte Carlo simulations demonstrate the advantages of this approach. Applying the proposed method to data on Italian middle schools indicates that school rankings are sensitive to prediction errors, even when extensive controls are added. RF estimates provide a low-cost way to increase the accuracy of predictions, resulting in more informative rankings, and better policies.

Keywords: value-added, school rankings, machine learning, Monte Carlo

JEL Classification: I21, C50

Suggested Citation

Sestito, Paolo and Schiltz, Fritz and Agasisti, Tommaso and De Witte, Kristof, The Added Value of More Accurate Predictions for School Rankings (February 4, 2019). Bank of Italy Temi di Discussione (Working Paper) No. 1209, February 2019, Available at SSRN: https://ssrn.com/abstract=3432393 or http://dx.doi.org/10.2139/ssrn.3432393

Paolo Sestito (Contact Author)

Bank of Italy ( email )

Via Nazionale 91
Rome, 00184
Italy

Fritz Schiltz

University of Leuven ( email )

Celestijnenlaan 200F
B-3001
Leuven
Belgium

Tommaso Agasisti

Politecnico di Milano - Department of Management, Economics and Industrial Engineering ( email )

Piazza Leonardo da Vinci
Milan, Milan 20133
Italy

Kristof De Witte

University of Leuven (KUL) ( email )

Naamsestraat 69
Leuven, Vlaams Brabant B-3000
Belgium

HOME PAGE: http://www.feb.kuleuven.be

Maastricht University ( email )

Boschstraat 24
Maastricht, Vlaams-Brabant 6211 AX
Netherlands
003216326656 (Phone)

HOME PAGE: http://www.feb.kuleuven.be

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
23
Abstract Views
261
PlumX Metrics