IDENTIFYING THE OUT OF CONTROL VARIABLE IN A MULTIVARIATE CONTROL CHART

ABSTRACT

The identification of the out of control variable, or variables, after a multivariate control chart signals, is an appealing subject for many researchers in the last years. In this paper we propose a new method for approaching this problem based on principal components analysis. Theoretical control limits are derived and a detailed investigation of the properties and the limitations of the new method is given. A graphical technique which can be applied in some of these limiting situations is also provided.     

ON THE EVALUATION OF CONTROL CHART LIMITS BASED ON PREDICTIVE DISTRIBUTIONS

ABSTRACT

We propose a Bayesian approach to obtaining control charts when there is parameter uncertainty. Our approach consists of two stages, (i) construction of the control chart where we use a predictive distribution based on a Bayesian approach to derive the rejection region, and (ii) evaluation of the control chart where we use a sampling theory approach to examine the performance of the control chart under various hypothetical specifications for the data generation model.     

An echelon inventory-based single-stage cost function for a two-station tandem system

We propose an alternative cost-accounting function for inventory control problems on a make-to-stock setting. Our proposal is based on observing that the traditional holding and backlog parameters introduce some odd short term distortions on the inventory state space. Our single-stage cost function accounts for echelon inventories and possesses a pair of cost parameters for each echelon inventory variable, depending on whether it is positive or negative. With the modified cost-accounting function, we study a twostation tandem system producing a single product, and investigate how it compares with the performances obtained with the usual single-stage cost function. The results available so far show that the optimal policies approach a multi-echelon base stock structure for each machine. Also, the service levels achieved are better under the modified function without increasing the levels of finished goods inventory.     

Job Strain, Effort-Reward Imbalance and Mental Distress: a study of occupations in general medical practice

There is increasing evidence to support the predictive power of social epidemiological models such as Effort-Reward Imbalance (Siegrist, 1996) and the Job-Strain Model (Karasek, and Theorell, 1990) for explaining occupational stress, although it has been suggested that the models may have distinctive contributions towards explaining work stress in specific work settings. Alternatively, it has been suggested that the explanatory power of the different models might be enhanced if they were combined. The aim of this paper is to explore these questions by examining the power of the two different models both separately and in combination for explaining job satisfaction and mental distress in general medical practice. This analysis was based on data collected from a postal survey of the members of staff (N=1089, response rate = 70%) of 81 practices, which were randomly selected from all general practices in the National Health Service Executive South East region. The results show that while both models were predictors of mental distress and job satisfaction the models that combined different dimensions were the strongest predictors.     

在发展中求质量—关于规模与质量问题的战略思考

本文是应邀在2001年国家高级教育行政学院“中德大学教育质量管理学术研讨会”上所作的演讲论文.论文以浙江师范大学为例,探讨了高等教育规模发展与质量保证之间存在的紧张关系和应对策略.论文的主要观点是,必须在发展的前提下重视质量问题,同时应将质量保证的工作落实到整个发展的过程中.     

RCBDs with a control

The randomized complete block designs, RCBDs, are among the most popular of block designs for comparing a set of experimental treatments. The question of this design's effectiveness when one of the treatments is a control is examined here. Optimality ranges are established for the RBCD in terms of the strength of interest in control comparisons. It is found that if the control treatment is of secondary interest, the RCBD, when not best, is typically near best. This is not so when comparisons with the control are of greater interest than those among the other treatments.     

Economic-Statistical Design of EWMA Control Charts Based on Taguchi's Loss Function

This paper proposes an economic-statistical design of the EWMA chart with time-varying control limits in which the Taguchi's quadratic loss function is incorporated into the economic-statistical design based on Lorenzen and Vance's economical model. A nonlinear programming with statistical performance constraints is developed and solved to minimize the expected total quality cost per unit time. This model, which is divided into three parts, depends on whether production continues during the period when the assignable cause is being searched for and/or repaired. Through a computational procedure, the optimal decision variables, including the sample size, the sampling interval, the control limit width, and the smoothing constant, can be solved for by each model. It is showed that the optimal economic-statistical design solution can be found from the set of optimal solutions obtained from the statistical design, and both the optimal sample size and sampling interval always decrease as the magnitude of shift increases.     

A framework for production control in health care organizations

The paper presents a hierarchical framework for production control of hospitals which deals with the balance between service and efficiency, at all levels of planning and control. The framework is based on an analysis of the design requirements for hospital production control systems. These design requirements are translated into the control functions at different levels of planning required for hospital production control. The framework consists of five levels of planning and control: patient planning and control, patient group planning and control, resources planning and control, patient volumes planning and control and strategic planning, though this last level does not make part of production control as such. Each of the levels of the framework is further elaborated in terms of the decisions made regarding patient flows and resources, and the co-ordination of the different planning levels. Implications of the framework are discussed by describing some points where current practice deviates from assumptions made in our approach. Recommendations for future research and development of the planning framework are formulated.     

Organization–public relationships: An exploration of the Sundre Petroleum Operators Group

This study explored the organization–public relationship (OPR) within the context of the Sundre Petroleum Operators Group (SPOG) and the local community in Sundre, Alberta, Canada. A qualitative orientation was adopted because of the case study's focus on the individual experience of the relationship and the interest was to explore how the relationship was perceived by the people involved. Key relational elements such as trust, transparency, dialogue, control mutuality, commitment and satisfaction were examined in relation to the importance for relationship building and maintenance. In-depth interviews were conducted with both SPOG industry and community members (N = 18). The results indicated that after a crisis transparency was critical for rebuilding trust which was the foundation for the development of the industry–community relationship. Other relational elements were also considered important for maintaining healthy OPRs, but were considered secondary in relation to trust.     

Weighted Dickey–Fuller processes for detecting stationarity

Aiming at monitoring a time series to detect stationarity as soon as possible, we introduce monitoring procedures based on kernel-weighted sequential Dickey–Fuller (DF) processes, and related stopping times, which may be called weighted DF control charts. Under rather weak assumptions, (functional) central limit theorems are established under the unit root null hypothesis and local-to-unity alternatives. For general dependent and heterogeneous innovation sequences the limit processes depend on a nuisance parameter. In this case of practical interest, one can use estimated control limits obtained from the estimated asymptotic law. Another easy-to-use approach is to transform the DF processes to obtain limit laws which are invariant with respect to the nuisance parameter. We provide asymptotic theory for both approaches and compare their statistical behavior in finite samples by simulation.