• Communications for Statistical Applications and Methods
• /
• 제20권2호
• /
• pp.107-113
• /
• 2013

This study reviews several well-known control charts for the location parameter with a discussion of the relationship between the maintenance of the control chart and a series of hypotheses testing. As a by-product, we then propose a new median control chart with the sign test statistic. We also modify the nonparametric control charts to easily understand the relation. Then we illustrate the construction of several median control charts with the industrial data and compare the efficiency among several control charts. Finally, we discuss some interesting features for the median control charts as concluding remarks.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.339-348
• /
• 2017

전통적인 통계적 공정관리에서 품질특성치의 위치모수와 척도모수의 변화를 탐지하는 것은 주된 관심사였고, 이를 위해 일반적으로 두 개의 관리도를 병행하여 사용한다. 그러나 하나의 관리도를 사용하여 두 모수의 변화를 동시에 탐지하는 절차에 대한 연구도 많이 진행되어 왔다. 하나 또는 두 개의 관리도를 사용할 때, 제1국면 (phase I)을 통하여 모수를 추정하여 관리한계를 설정하여 제2국면(phase II)의 관리도를 운영하는데 이때 정규성 가정의 만족 여부는 아주 중요한 점검 사항이다. 실제 공정에서는 종종 분포에 대한 가정을 하기 어렵거나 정규분포를 따른다고 가정하기 어려운 경우가 있는데, 이러한 경우에는 비모수적 관리도를 사용할 수 있다. 이 논문에서는 비모수적 관리도이면서, 하나의 관리도를 사용하여 위치모수와 척도모수의 변화를 탐지하는 Shewhart-Lepage 관리도를 소개하고, 위치모수와 척도모수가 동시에 변화할 때 진단 단계에서 변화의 원인을 가장 정확하게 진단할 수 있는 최적의 진단한계를 모의실험을 통해 제시하고 그 효율에 대해 연구하였다.

• Journal of the Korean Statistical Society
• /
• 제14권2호
• /
• pp.76-86
• /
• 1985

Shewhart X-chart, which is most widely used in practice, is shown to be inappropriate for the cases where the process distribution is one-sided asymmetrical, and thus some nonparametric Shewhart type charts are developed instead. These schemes may be applied usefully when there is not enough information in determining the process distribution. The average run lengths are obtained to compare the efficiency of control charts for various shifts of the location parameter and for some typical one-sided asymmetrical distributions.

• Smart Structures and Systems
• /
• 제14권3호
• /
• pp.377-395
• /
• 2014

Vibration-based fault detection and condition monitoring of rotating machinery, using statistical process control (SPC) combined with statistical pattern recognition methodology, has been widely investigated by many researchers. In particular, the discrete wavelet transform (DWT) is considered as a powerful tool for feature extraction in detecting fault on rotating machinery. Although DWT significantly reduces the dimensionality of the data, the number of retained wavelet features can still be significantly large. Then, the use of standard multivariate SPC techniques is not advised, because the sample covariance matrix is likely to be singular, so that the common multivariate statistics cannot be calculated. Even though many feature-based SPC methods have been introduced to tackle this deficiency, most methods require a parametric distributional assumption that restricts their feasibility to specific problems of process control, and thus limit their application. This study proposes a nonparametric multivariate control chart method, based on multiscale wavelet scalogram (MWS) features, that overcomes the limitation posed by the parametric assumption in existing SPC methods. The presented approach takes advantage of multi-resolution analysis using DWT, and obtains MWS features with significantly low dimensionality. We calculate Hotelling's $T^2$-type monitoring statistic using MWS, which has enough damage-discrimination ability. A bootstrap approach is used to determine the upper control limit of the monitoring statistic, without any distributional assumption. Numerical simulations demonstrate the performance of the proposed control charting method, under various damage-level scenarios for a bearing system.

• Journal of Preventive Medicine and Public Health
• /
• 제44권3호
• /
• pp.101-110
• /
• 2011

Objectives: Screening for colorectal cancer is considered cost effective, but is underutilized in the U.S. Information on the efficiency of "tailored interventions" to promote colorectal cancer screening in primary care settings is limited. The paper reports the results of a cost effectiveness analysis that compared a survey-only control group to a Centers for Disease Control (CDC) web-based intervention (screen for life) and to a tailored interactive computer-based intervention. Methods: A randomized controlled trial of people 50 and over, was conducted to test the interventions. The sample was 1224 partcipants 50-70 years of age, recruited from Kelsey-Seybold Clinic, a large multi-specialty clinic in Houston, Texas. Screening status was obtained by medical chart review after a 12-month follow-up period. An "intention to treat" analysis and micro costing from the patient and provider perspectives were used to estimate the costs and effects. Analysis of statistical uncertainty was conducted using nonparametric bootstrapping. Results: The estimated cost of implementing the web-based intervention was $40 per person and the cost of the tailored intervention was $45 per person. The additional cost per person screened for the web-based intervention compared to no intervention was $2602 and the tailored intervention was no more effective than the web-based strategy. Conclusions: The tailored intervention was less cost-effective than the web-based intervention for colorectal cancer screening promotion. The web-based intervention was less cost-effective than previous studies of in-reach colorectal cancer screening promotion. Researchers need to continue developing and evaluating the effectiveness and costeffectiveness of interventions to increase colorectal cancer screening.