Change point detection to analyze air pollution and its economic effects: an exponentially weighted moving average perspective

Air pollution has a direct impact on every society, leading to consequential effects on a nation's economy. The repercussions of poor air quality on human health can lead to various economic outcomes, such as rising healthcare costs, diminished labor productivity, negative effects on tourism and living standards, increased regulatory expenses for businesses, and heightened economic disparities. An essential control method is required to monitor those situations that influence the economy, including air quality as well. The presence of toxic substances in the air causes pollution that diminishes the air quality. It is necessary to monitor air pollution through indices like PM10 using efficient change point detection tools, among which a control chart is the most famous monitoring tool of the statistical process tool kit. This study designs a new process monitoring tool that uses the additional information available, if any, other than the main variable of interest. Moreover, it is ensured that the detection ability of the proposed methodology is uncompromised due to disturbances in the side variable. Interestingly, it is shown mathematically that many existing statistical quality control tools become special cases of the designed structure at specific values of sensitivity parameter. The proposed structure is evaluated in terms of properties of run length distribution. It is observed that the robustness-efficiency balance can be controlled by adjusting the sensitivity parameter of the proposed chart. As a practical example, the proposal's implementation is demonstrated for monitoring air quality data.