In Bazemore v. Friday, 478 U.S. 385 (1986), a case involving pay discrimination in the North Carolina Extension Service, the plaintiff, a group of black agents, submitted a multiple regression model showing that, on average, the black agents' salary was lower than that of their white counterparts. When the case reached the court of appeals, it rejected the plaintiff's case on the grounds that their regression had not included all the variables thought to have an effect on salary. The Supreme Court, however, reversed the appeals court. It stated:
The Court of Appeals erred in stating that petitioners'regression analyses were "unacceptable as evidence of discrimination", because they did not include all measurable variables thought to have an effect on salary level. The court's view of the evidentiary value of the regression analysis was plainly incorrect. While the omission of variables from a regression analysis may render the analysis less probative than it otherwise might be, it can hardly be said, absent from infirmity, that an analysis which accounts for major factors "must be considered unacceptable as evidence of discrimination." Ibid. Normally, a failure to include variables will affect the analysis - probativeness, not its admissibility.
Explain why you agree or disagree with the Supreme Court decision.
The Supreme Court decision reversed the lower court's ruling that there was no evidence of discrimination. Thus it found for the plaintiffs, enabling them to recover the wages lost because of the alleged dual-pay system that paid whites more than blacks.
In order to determine whether this was a good decision, we need to look at the statistical reasoning behind it, because the regression analysis was the basis of the plaintiffs' claim that they were not fairly compensated. If you agree that the regression analysis was properly done, then the Supreme court's decision was good. If you think it was faulty, as ...