Implementing Anti-Discrimination Policies in Statistical Profiling Models
- 1 August 2011
- journal article
- Published by American Economic Association in American Economic Journal: Economic Policy
- Vol. 3 (3) , 206-231
Abstract
How should statistical models used for assigning prices or eligibility be implemented when there is concern about discrimination? In many settings, factors such as race, gender, and age are prohibited. However, the use of variables that correlate with these omitted characteristics (e.g., zip codes, credit scores) is often contentious. We provide a framework to address these issues and propose a method that can eliminate proxy effects while maintaining predictive accuracy relative to an approach that restricts the use of contentious variables outright. We illustrate the value of our proposed method using data from the Worker Profiling and Reemployment Services system. (JEL C53, J15, J65, J71)Keywords
This publication has 7 references indexed in Scilit:
- Implementing Anti-Discrimination Policies in Statistical Profiling ModelsAmerican Economic Journal: Economic Policy, 2011
- Is the Threat of Reemployment Services More Effective Than the Services Themselves? Evidence from Random Assignment in the UI SystemAmerican Economic Review, 2003
- Does Banning Affirmative Action Lower College Student Quality?American Economic Review, 2003
- Extended benefits and the duration of UI spells: evidence from the New Jersey extended benefit programJournal of Public Economics, 2000
- Early reemployment for dislocated workers in the United StatesInternational Social Security Review, 1997
- The Enforcement of Equal Opportunity Laws Under Imperfect Information: Affirmative Action and AlternativesThe Quarterly Journal of Economics, 1991
- Specification Error in Probit ModelsReview of Economics and Statistics, 1985