Homogeneously Weighted Moving Average Control Chart

Statistical process control possesses some tools that can be used to monitor the variations in a process. One of these tools is the control chart which is further categorized into memory less and memory control charts. The memory less control charts are designed to detect the larger disturbances in the process and the memory control charts are good at quickly detecting the presence of smaller and moderate disturbances. This paper introduces a new memory-type control chart named as homogeneously weighted moving average control chart used for the monitoring of process location. The proposal is an improvement to the already existing exponentially weighted moving average control chart. The performance of the proposed chart will be measured in terms of average run length, extra quadratic loss, ratio of average run length and performance comparison index. Due to the fact that normality is not guaranteed in every real life process, the effect of non-normality on the performance of proposed chart will be assessed using Gamma and Students t distributions. The evaluated performance will be then compared with some existing memory-type control charts and the superiority regions of the proposed chart will be established. Finally, the application of the proposed chart will be demonstrated using a real dataset.