Inez M. Zwetsloot

Another Look at the EWMA Control Chart with Estimated Parameters

When in-control process parameters are estimated, Phase II control chart performance will vary among practitioners due to the use of different Phase I data sets. The typical measure of Phase II control chart performance, the average run length (ARL), becomes a random variable due to the selection of a Phase I data set for estimation. Aspects of the ARL distribution, such as the standard deviation of the average run length (SDARL), can be used to quantify the between-practitioner variability in control chart performance. In this article, we assess the in-control performance of the exponentially weighted moving average (EWMA) control chart in terms of the SDARL and percentiles of the ARL distribution when the process parameters are estimated. Our results show that the EWMA chart requires a much larger amount of Phase I data than previously recommended in the literature in order to sufficiently reduce the variation in the chart performance. We show that larger values of the EWMA smoothing constant result in higher levels of variability in the in-control ARL distribution; thus, more Phase I data are required for charts with larger smoothing constants. Because it could be extremely difficult to lower the variation in the in-control ARL values sufficiently due to practical limitations on the amount of the Phase I data, we recommend an alternative design criterion and a procedure based on the bootstrap approach.

CUSUM charts with controlled conditional performance under estimated parameters

ABSTRACT We study the effect of the Phase I estimation error on the cumulative sum (CUSUM) chart. Impractically large amounts of Phase I data are needed to sufficiently reduce the variation in the in-control average run lengths (ARL) between practitioners. To reduce the effect of estimation error on the charts performance we design the CUSUM chart such that the in-control ARL exceeds a desired value with a specified probability. This is achieved by adjusting the control limits using a bootstrap-based design technique. Such approach does affect the out-of-control performance of the chart; however, we find that this effect is relatively small.

A robust estimator for location in Phase I based on an EWMA chart

In practice, a control chart for process monitoring (Phase II) is based on parameters estimated from data collected on the process characteristic under study (Phase I). The Phase I data could contain unacceptable data, which in turn could affect the monitoring. In this study, we consider various estimation methods that are potentially relevant within the parameter estimation process. The quality of the Phase I study is evaluated in terms of the precision of the resulting estimates as well as the effectiveness of the exploratory data analysis, where ‘effectiveness’ is measured by the proportion of observations that are correctly identified as unacceptable. Moreover, we study the impact of the Phase I estimation method on the performance of the EWMA control chart in Phase II.

A robust Phase I exponentially weighted moving average chart for dispersion

APhaseIestimatorofthedispersionshouldbeefficientunderin-controldataandrobustagainstcontaminations.Mostestimation methods proposed in the literature are either efficient or robust against either sustained shifts or scattered disturbances. In this article, we propose a new estimation method of the dispersion parameter, based on exponentially weighted moving average charting, which is efficient and robust to both types of unacceptable observations in Phase I. We compare the method with various existing estimation methods and show that the proposed method has the best overall performance if it is unknown what type of contaminations are present in Phase I. We also study the effect of the robust estimator from Phase I on the Phase II exponentially weighted moving average control chart performance. Copyright

A head-to-head comparative study of the conditional performance of control charts based on estimated parameters

ABSTRACT Implementation of the Shewhart, CUSUM, and EWMA charts requires estimates of the in-control process parameters. Many researchers have shown that estimation error strongly influences the performance of these charts. However, a given amount of estimation error may differ in effect across charts. Therefore, we perform a pairwise comparison of the effect of estimation error across these charts. We conclude that the Shewhart chart is more strongly affected by estimation error than the CUSUM and EWMA charts. Furthermore, we show that the general belief that the CUSUM and EWMA charts have similar performance no longer holds under estimated parameters.

Decreasing the dispatch time of medical reports sent from hospital to primary care with Lean Six Sigma.

RATIONALE, AIMS AND OBJECTIVES Timely communication is important to ensure high-quality health care. To facilitate this, the Gastro Intestinal Oncology Center Amsterdam (GIOCA) stipulated to dispatch medical reports on the day of the patients visit. However, with the increasing number of patients, administrative processes at GIOCA were under pressure, and this standard was not met for the majority of patients. The aim and objective of this study was to dispatch 90% of medical reports on the day of the patients visit by improving the logistic process. METHODS To assess the main causes for a prolonged dispatch time and to design improvements actions, the roadmap offered by Lean Six Sigma (LSS) was used, consisting of five phases: Define, Measure, Analyze, Improve and Control (DMAIC roadmap). RESULTS Initially, 12.3% of the reports were dispatched on the day of the patients visit. Three causes for a prolonged dispatch time were identified: (1) determining which doctors involved with treatment would compose the report; (2) the reports composed by a senior resident had to be reviewed by a medical specialist; and (3) a medical specialist had to authorize the administration to dispatch the reports. To circumvent these causes, a digital form was implemented in the electronic medical record that could be completed during the multidisciplinary team meeting. After implementation, 90.6% of the reports were dispatched on the day of the visit. CONCLUSION The dispatch time of reports sent from hospital to primary care can be significantly reduced using Lean Six Sigma, improving the communication between hospital and primary care.

Robust point location estimators for the EWMA control chart

Abstract In practice, the EWMA control chart for process monitoring is based on parameters estimated from a retrospective data set representing the process characteristic under study. This data set may contain contaminated observations, which in turn can affect the estimates and hence the control chart’s performance. We study the problem of estimating the location when the data set may or may not contain contaminated observations. We compare six point estimators proposed in the SPC literature. The quality of the estimators is evaluated in terms of estimation accuracy. Moreover, we study the impact of the estimators on the performance of the EWMA control chart based on the different location estimators.

Quality Quandaries: improving revenue by attracting more clients online

This article provides an example of a Lean Six Sigma project with respect to online marketing.

Quality Quandaries: Increasing the First Time Fix Rate in a Customer Contact Center

This column discusses a Lean Six Sigma improvement project in the contact center of a medium-sized bank (€7.5 billion in annual turnover and €170 billion in assets under management; ABN AMRO Group 2013). The goal of the project was to increase the first..

Discussion of “Quality and statistical thinking in a parliament and beyond”

First of all, we would like to thank Pedro Saraiva for his excellent talk at the Fifth Stu Hunter Research Conference in Copenhagen, Denmark. The topic is highly relevant in practice, and the proposed solutions yield great opportunities. In this article, we provide some remarks and suggestions related to the proposal. We respond to his Stu Hunter Research Conference paper (Saraiva 2018) where the positive effects of statistical thinking (Snee and Hoerl 2003) on political processes in Portugal are demonstrated. In response to the findings and conclusions of Saraiva about the added value of statistical thinking and the application of quality management tools, we share our experience on implementing operational excellence projects in the public (administration) sector. Since 1996 the Institute for Business and Industrial Statistics (IBIS UvA), an independent consulting bureau within the University of Amsterdam, has been involved in the implementation of many operational excellence projects in organizations in the public sector. This ranges from organizations where unemployment benefits are processed, to agencies responsible for managing the temporarily unfit for work, to local municipality administrations. In all of these organizations we have observed a potential for efficiency and effectiveness improvement and we believe that there is a growing need for organizations in the public sector to further improve their operations. This is corroborated by the international trend of introducing performance measurement and private sector management techniques to increase operational performance (Speklé and Verbeeten 2014) in the public sector.