Using the Laney p’ Control Chart for Monitoring COVID-19 Cases in Jordan

Abstract

In this research, we examine the use of the Laney p’ control chart and the application of test rules to assess governmental interventions throughout the COVID-19 pandemic and understand how certain activities and events that took place affected the infection rate. Data for the infection rate (IR) were collected between October 31, 2020, and March 19, 2022. The IR was calculated by dividing the number of confirmed cases by the number of PCR (polymerase chain reaction) tests performed. The IR data were subsequently plotted on the Laney p’ control charts using the Minitab software. The charts thereby allowed us to study the effects on infection rates of the government’s moves to restrict the movements and activities of the population, as well as the results of easing these restrictions. The restrictive measures proved to be effective in decreasing the infection rate, whereas relaxing these measures had the opposite effect. Typically, test signals are considered as an indication of a change in a process, although in some situations we have observed that slight changes are not accompanied by a signal. Regardless, the analysis shows cases where using test rules rapidly detected patterns and changes in IR, and allowing remedial action to be taken without delay. In this study, we use the Laney p’ control chart to monitor the COVID-19 IR and compare its performance with that of the EWMA control chart. In addition, we analyze the performance of various test rules in detecting IR changes. Comparing the Laney p’ control chart with the EWMA control chart, the data showed that in most cases, the Laney p’ control chart was able to identify the change of IR faster. Comparing the performance of different tests in detecting changes in the IR, one can see that no particular test outperformed the others in all cases. We also recommend analyzing the data points in both single-stage and multistage analyses in accordance with this new perspective rather than the traditional one used in process improvement projects. Accordingly, the single-stage analysis gives a complete picture of how the infection rate is changing overall, whereas the multistage analysis is more sensitive to small changes.