A New Metric To Quantify Interchangeability of Measurement Systems

Image

In the article, titled “Assessing Agreement Between Two Measurement Systems,” Stevens and his coauthors “consider the problem of comparing a new measurement system with an existing one to ensure they agree sufficiently to be used interchangeably...[and] propose a new metric, the probability of agreement, that more effectively and transparently quantifies agreement than do existing methods.”

This new metric would function as a new alternative to Bland and Altman’s popular “limits of agreement” approach, which has been cited over 30,000 times, according to Stevens.

This article is expected to appear in the November or December issue of Statistical Methods in Medical Research, but has been published online ahead of print as of Sept. 2.

Being Smart About Parts

Stevens also, earlier this year, published an article in the March issue of Quality Progress.

“In medical, manufacturing and other contexts, the importance of an accurate and precise measurement device is paramount,” he said. “In order to assess the quality of a measurement system, a Measurement System Assessment Study must be undertaken.”

In the article, “Being Smart About Parts,” he and his coauthors “suggest a novel experimental design that, by leveraging historical data, is simpler and more cost effective than existing experiments, and provides more information about a measurement system’s quality,” he said.

Stevens teaches jointly in the Mathematics and Statistics department and the MS in Analytics (MSAN) program.

References
Stevens N.T., Steiner S.H., and MacKay R.J. “Assessing Agreement Between two Measurement Systems: An Alternative to the Limits of Agreement Approach”. Statistical Methods in Medical Research, (September 2, 2015), doi: 10.1177/0962280215601133.

Stevens N.T., Steiner S.H., and MacKay R.J. “Being Smart About Parts”, Quality Progress, 2015, March, 32–37.