Layman’s abstract for QREI paper: Transferring biological sequence analysis tools to break‐point detection for on‐line monitoring

Each week, we will be publishing layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.

The article featured today is from Quality and Reliability Engineering International, with the full article now available to read on Early View here.

Mercier, S. Transferring biological sequence analysis tools to break‐point detection for on‐line monitoring: A control chart based on the local score. Qual Reliab Engng Int. 2020; 1– 19. https://doi.org/10.1002/qre.2703

Atypical regions or break-point detection has been largely studied in many diverse application fields. It can be a sequential (on-line) analysis where the data is discovered progressively, as in quality process monitoring, global navigation satellite systems, medical and public health surveillance, queuing theory. Or it can be an analysis of the whole sequence at one time, as in biological sequence analysis or geo statistics. It can also be a mixed approach like in epidemiology. The already developed tools have each their own advantages, their drawbacks and application constraints. We propose here to transfer and adapt the mathematical tool largely used to highlight atypical region in biological sequences, called the local score, to the detection of breakpoints in on-line analysis and more precisely to Statistical Process Control. We present a control chart based on the Local Score statistic. Theoretical results on its distribution allow us to distinguish atypical observation form the ones which have appeared by chance and to declare if the process is statistically in-control or not. Performance of this chart is then compared to the best ones proposed at the present time in the literature. The study exhibits dominance of the Local Score chart. Very interesting openings are also presented.