Is 'Above Average' Provider Performance Better Than 'Average' Performance?

• Activity Number: 328
• Type: Topic Contributed
• Date/Time: Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Susan Paddock*+ and Fernando Hoces de la Guardia and John L. Adams
• Companies: RAND Corporation and Pardee RAND Graduate School and Kaiser Permanente

Abstract

Addressing uncertainty in public reports of health care provider performance is important. A typical approach to do so is to divide providers into three performance tiers: significantly above average; significantly below average; or not significantly different from average. Consumers of public reports may fail to appreciate that the difference between an above-average and an average provider may not be significant. While public reports frequently provide cautions against making interpretations not supported by the underlying data analysis, consumers may lack the technical knowledge required to appreciate these cautions. Though some public reports allow consumers to compare a small number of providers side-by-side, such information is typically presented without a formal assessment of the significance of such comparisons. We will discuss these issues and their implications; explore conditions under which public reports can be designed to minimize the opportunities for misinterpretation of results; and discuss alternative analytic approaches for public reporting websites. We will also discuss how this issue applies more broadly to other public report designs.