ABSTRACT
When separate populations exhibit similar reliability as a function of multiple explanatory variables, combining them into a single population is tempting. This can simplify future predictions and reduce uncertainty associated with estimation. However, combining these populations may introduce bias if the underlying relationships are in fact different. The probability of agreement formally and intuitively quantifies the similarity of estimated reliability surfaces across a two-factor input space. An example from the reliability literature demonstrates the utility of the approach when deciding whether to combine two populations or to keep them as distinct. New graphical summaries provide strategies for visualizing the results.
Additional information
Notes on contributors
Nathaniel T. Stevens
Nathaniel T. Stevens is an assistant professor of statistics at the University of San Francisco, in the bachelor of data science and master of analytics programs. His research interests include measurement system analysis, experimental design, and statistical process monitoring. He was the 2014 recipient of ASA's Mary G. and Joseph Natrella award and the 2012 recipient of ASQ's Ellis R. Ott award for applied statistics and quality management. He is a member of the ASQ.
Christine M. Anderson-Cook
Christine M. Anderson-Cook is a research scientist in the Statistical Sciences Group at Los Alamos National Laboratory. She currently leads projects in the areas of complex system reliability, non-proliferation, malware detection, and statistical process control. Her research interests include response surface methodology, design of experiments, reliability, multiple criterion optimization, and graphical methods. She is an elected fellow of the American Statistical Association and the American Society for Quality. In 2012, she was honored with the ASQ Statistics Division William G. Hunter Award.