View Proposal


Proposer
Teoh Wei Lin
Title
Exact run length distribution of the variable sampling interval EWMA X̅ chart with know and estimated process parameters
Goal
To compute the percentiles of the run length distribution for the variable sampling interval EWMA X̅ chart
Description
A control chart is an excellent process monitoring technique to reduce variability in key parameters. A well-designed control chart enables practitioners to quickly detect process shifts before manufacturing many nonconforming products. Since the run length distribution is generally highly skewed, a significant concern about focusing too much on the average-time-to-signal (ATS) criterion is that we may miss some crucial information about a control chart’s performance. Thus, it is important to investigate the entire time-to-signal distribution of a control chart for an in-depth understanding before implementing the chart in process monitoring. In this project, the percentiles of the time-to-signal distribution for the EWMA X̅ chart with known and estimated process parameters are computed. Knowledge of the percentiles of the tome-to-signal distribution provides a more comprehensive understanding of the expected behaviour of the time to signal. This additional information includes the early false alarm, the skewness of the time-to-signal distribution, and the median time to signal (MTS). In this project, student needs to develop the theoretical and simulation computer programming coding using R or selected programming software.
Resources
Montgomery, D.C. (2013). Statistical Quality Control: A Modern Introduction, 7th ed., New York: John Wiley & Sons.
Background
The dataset adopted from Montgomery (2013) will be utilized in the application example section to illustrate the plotting of the variable sampling interval EWMA X̅ chart in the report.
Url
External Link
Difficulty Level
Moderate
Ethical Approval
None
Number Of Students
1
Supervisor
Teoh Wei Lin
Keywords
statistical process control, variable sampling interval ewma x̅ chart, percentiles of the run length distribution, parameter estimation
Degrees
Bachelor of Science in Statistical Data Science