Formal Statistical Analysis Provides Sounder Inferences Than the U.S. Government's 'Four-Fifths Rule': Examining the Data from Ricci v. DeStefano

• Activity Number: 488
• Type: Invited
• Date/Time: Wednesday, August 4, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Committee on Law and Justice Statistics
• Author(s): Weiwen Miao*+ and Joseph L. Gastwirth
• Companies: Haverford College and Washington University

Abstract

The data from Ricci v. DeStefano will be discussed from a formal statistical point of view. The City of New Haven was sued because it canceled the exams after seeing that no African-American could be appointed to an existing vacancy. The City justified its action on the basis that the promotion exams had a disparate impact on minorities because the ratios of their pass rates to that of Whites were less than 80%, contrary to a "rule of thumb" in the government's Uniform Guidelines. Unfortunately, neither party used statistical tests. Formal statistical analysis shows that the lieutenant exam had a disparate impact on minorities, but the differences in the pass rates on the captain exam were not close to statistical significance. Our analysis shows that the government's "Four-fifth" rule should not be used when the sample sizes are small.