ORLANDO, Fla. (AP) – Hold onto your calculators, statisticians!
After three years of fierce debates, conflicting academic papers and a lawsuit, the U.S. Census Bureau on Wednesday announced guidelines for how a controversial statistical method will be applied to the numbers used for drawing congressional and legislative districts. The method is meant to protect the privacy of people who participated in the 2020 census, though critics have claimed it favors confidentiality at the expense of accurate numbers.
The privacy method adds controlled “noise,” or intentional errors, to the data to obscure the identity of any given participant in the 2020 census while still providing statistically valid information. The final guidelines announced by the Census Bureau weigh more in favor of accuracy than privacy compared to past test versions released by the statistical agency that interested parties have been evaluating.
The debate over the method known as differential privacy has resulted in a nerd knife-fight of sorts among statisticians, demographers and the redistricting experts who argued over whether its application would make unusable the numbers used for redrawing congressional and legislative districts. Release of the specific guidelines could further intensify the ongoing debate about the accuracy of numbers gathered during a national headcount that took place in the midst of a global pandemic and an already supercharged political climate.
If you picture the privacy tool as a dial with lower settings offering the most privacy and higher settings providing the most accuracy, the Census Bureau dialed up the accuracy in the final guidelines. The statistical term for this dial is “epsilon,” and the bureau settled on an epsilon of 19.61, significantly higher than where the dial was set in earlier versions that critics raised concerns about.