Skip to main content

Measure Testing


Information from testing often provides additional empirical evidence to support prior judgments of a measure’s importance. In particular, beta testing results may reveal that a measure assesses an area with substantial opportunities for improvement. Testing can also uncover that the measure addresses a high-impact or meaningful aspect of health care.

Examples of Empirical Evidence

Examples of empirical evidence for importance or improvement opportunities derived from testing data include

  • Quantifying the frequency or cost of measured events to demonstrate no measurement of rare or low-cost events 
  • Identifying substantial variation among comparison groups or suboptimal performance for a large portion of the groups
  • Demonstrating that methods for scoring and analysis of the measure allow for identification of statistically significant and practically/clinically meaningful differences in performance
  • Showing disparities in care related to race, ethnicity, gender, income, or other classifiers
  • Identifying evidence that a measure is associated with consistent delivery of effective processes or access that leads to improved outcomes

Examples of Reported Data

Reported data to support the importance of a measure may include

  • Descriptive statistics (e.g., means, medians, standard deviations, confidence intervals for proportions, percentiles) to demonstrate the existence of gaps or disparities.
  • Analyses to quantify the amount of variation due to comparison groups such as rural versus urban through R2 or intraclass correlation.

Last Updated: