Hsi-Tien Chen

Statistical testing for assessing the performance of lifetime index of electronic components with exponential distribution

The electronics industry has heavily prioritized enhancing the quality, lifetime and conforming rate (conforming to specifications) of electronic components. Various methods have been developed for assessing quality performance. In practice, process capability indices (PCIs) are used as a means of measuring process potential and performance. Moreover, most PCIs have been developed or investigated under the assumption that electronic components have a lifetime with a normal distribution. However, PCIs for non‐normal distributions have seldom been discussed. Nevertheless, the lifetime of electronic components generally may possess an exponential, gamma or Weibull distribution and so forth. Under an exponential distribution, some properties of the PCIs and their estimators differ from those in a normal distribution. To utilize the PCIs more reasonably and accurately in assessing the lifetime performance of electronic components, this study constructs a uniformly minimum variance unbiased (UMVU) estimator of their lifetime performance index under an exponential distribution. The UMVU estimator of the lifetime performance index is then utilized to develop the hypothesis testing procedure. The purchasers can then employ the testing procedure to determine whether the lifetime of the electronic components adheres to the required level. Manufacturers can also utilize this procedure to enhance process capability.

A MAIC approach to TFT-LCD panel quality improvement

Abstract The liquid crystal displays (LCDs) possess the most mature technology and best consuming competitiveness in the flat panel display (FPD) industries. Of all the LCDs, thin film transistor-liquid crystal display (TFT-LCD) keeps some real advantages. It is thinner, smaller and lighter than other displays and has low power consumption, low-radiation, high-contrast and high-dpi at the same time. Hence, the TFT-LCD panel is widely applied in daily electronic products, and the demand for the TFT-LCD panel increases. The product life cycle of the TFT-LCD panel is gradually getting into the mature stage, and meanwhile, Taiwan’s firms face fierce competition from South Korea and Japan. Thus, at present, continual cost reduction is an all-out pursuing topic for Taiwan’s panel manufacturers. If the quality and yield of the TFT-LCD panel can be effectively enhanced, the non-conforming rate and the cost of the TFT-LCD panel will be reduced. In this study, TFT-LCD panel manufacturing process is discussed, and then five critical-to-quality (CTQ) characteristics (or sub-processes) are identified and summarized. At the early stages, the assessing model of process quality index ( C pm ) and the MAIC (i.e., measure-analyze-improve-control) approach of Six Sigma are used to measure and analyze the CTQ characteristics that make TFT-LCD panel unqualified and incapable. During the later stages, Hartley’s homogeneity test and joint confidence intervals were conducted to determine the optimal parameter setting of the critical factor in TFT-LCD panel manufacturing process. By using these optimal settings, Six Sigma quality level can be achieved.

Applying Importance–Performance Analysis With Simple Regression Model and Priority Indices to Assess Hotels' Service Performance

The purpose of this study was to propose a revised importance–performance analysis (RIPA) grid to improve the weaknesses of self-stated (or implicitly derived) importance and improvement (or resource reallocation) priority for service attributes in importance–performance analyses (IPAs). The importance derived from simple linear regression analyses was used to replace self-stated or implicit importance derived from multiple regression (or partial correlation) analyses in order to construct the RIPA grid, which not only measures attribute importance and performance but also easily and effectively identifies service management strategies. Also, this paper proposes improvement and resource reallocation priority indices to more effectively prioritize the improvement and resource reallocation of service attributes located in the “Concentrate Here” and “Possible Overkill” quadrants, respectively. A case study of tourist hotels is presented to demonstrate the application of the RIPA. The analyzed results show that the simple regression coefficients of all attributes were positive, but some multiple regression coefficients and partial correlation coefficients were negative. It revealed that using multiple regression analysis or partial correlation analysis to estimate attribute importance might be inappropriate, and simple linear regression analysis might be more reasonable in RIPA. The effective and appropriate action scheme for each service attribute can then be acquired using the RIPA approach. The study offers new insights into the attribute importance and improvement/reallocation priority in importance–performance analysis, resolves IPA grid weaknesses, and provides industries with a simple and useful management tool.

Advanced multi-process performance analysis chart for an entire product with joint confidence regions

The control charts are widely used to control the process stability, and then analyse the ‘in-control’ data in the statistical process control. However, an ‘in-control’ process is not enough since it can produce non-conforming or out of specification products. Process capability indices, like Cp , Cpu , Cpl and Cpk , have been proposed to make decisions on how well the process meets specifications in practice. These indices can not be straightforwardly used for illustrating and analysing the multi-process products. Hence, the multi-process performance analysis chart (MPPAC) has been proposed. Nevertheless, the MPPAC approach is not reliable since sampling errors are ignored, and PCAC is only just suitable for full inspection. To overcome these shortcomings, this paper aims to develop an advanced multi-process performance analysis chart (AMPPAC) with process capability zones as well as taking into account interval estimates of these indices for precisely measuring an entire product composed of symmetric tolerances, larger-the-better and smaller-the-better characteristics. Besides, the issue about independent processes has been proposed by Chen et al . (Chen, K.S., Huang, M.L. and Li, R.K., Process capability analysis for an entire product. Int. J. Prod. Res., 2001, 39(17), 4077–4087.), and the solution about dependent processes will be provided in this paper. Thus, the AMPPAC can reliably and appropriately assess the multi-process performance and provide chances for continuous improvement on the manufacturing process.

Applying a revised SQPM in the Define Step of Six Sigma and a case study

The primary purpose of this paper is to construct a revised service quality performance matrix (SQPM) approach as an effective and objective tool in the Define Step of Six Sigma projects. This approach can then overcome the shortcomings of the SQPM proposed by Hung, Huang, and Chen [(2003). Service quality evaluation by service quality performance matrix. Total Quality Management, 14(1), 79–89] such as time-consuming questionnaire items, and the percentage scale and self-stated attribute importance. Other general purposes of this paper are to establish the implementation process of the revised SQPM approach, apply this approach and process in the Define Step of Six Sigma projects (Define, Measure, Analyse, Improve and Control framework), and a case study with regard to a campus restaurant which is ultimately presented to demonstrate the application of the above methodology in practice. The approach and process are simple, effective and objective for identifying critical-to-quality service dimensions (or attributes) and their improvement priority. Additionally, they can enhance the operators decision-making quality of service strategies.

A paired-test method to verify service speed improvement in the Six Sigma approach: a restaurant's case study

The current study aims to propose a paired-test method of order statistics which is a non-parametric statistics approach to compensate for the academic gap in the measure step of Six Sigma projects. Another aim of this paper is to present a case study regarding a campus restaurant to demonstrate the application of the proposed method and Six Sigma processes. The theoretical basis of the proposed method was presented and new Six Sigma define-measure-analyse-improve-measure-control processes were conducted. The proposed method can effectively identify the improvement effectiveness of service speeds before and after Six Sigma project execution. The Six Sigma processes can be applied by other industries for problem-solving.

A Study of Process Quality Assessment for Golf Club-Shaft in Leisure Sport Industries

Effective management of process quality is crucial for attracting customers and maintaining their loyalty, and the quantification of quality for processes with multiple characteristics has recently been receiving considerable attention. This paper proposes a comprehensive process quality index to provide numerical measures for the precision, accuracy, and performance of processes in the manufacturing of golf club-shafts, using both smaller-the-better type and symmetric nominal-the-best type characteristics. The point estimates of these indices were replaced with joint confidence blocks in order to overcome a lack of reliability. Based on this index, we developed a control chart with process capability zones describing joint confidence blocks of all characteristics related to golf club-shafts within a single chart. Finally, we present an assessment procedure and illustrated examples with which to evaluate the process quality for the manufacture of golf club-shaft. The results reveal that the straightness and torsion of the club-shaft are “out of control” and unqualified, whereas the length, tip outer circumference, and butt outer circumference of the club-shaft are categorized as “excessive.” The application of this chart enables engineers involved in the manufacturing of golf equipment to simultaneously monitor and control the quality characteristics of golf club-shafts.

The construction and application of Six Sigma quality indices

Process quality is the primary factor in facilitating product sales. In accordance with the concept of Six Sigma, numerous studies have employed process capability indices for the determination of process quality levels. Unfortunately, existing indices present only a range of quality levels rather than a specific quality level value. This paper aims to propose Six Sigma quality indices for the assessment of quality levels associated with unilateral as well as bilateral specifications. To ensure the reliability in process assessment, we employ the lower confidence limit of the indices to serve as a standard and develop a process quality analysis chart for the simultaneous evaluation of larger-the-better, smaller-the-better and nominal-the-best quality characteristics with the aim of identifying the causes of sub-standard quality. The resulting chart also provides a valuable reference by which to guide efforts aimed at improvement. Finally, we present three cases and numerical experiments to demonstrate the practical applicability of the proposed method.

A New Service Performance Index Based on Time Interval of Complaints

Customer satisfaction plays a key role in enterprises gaining a competitive advantage. Both industrial and academic fields are focusing increasing attention on finding proper methods to evaluate service performance. Because service performance is directly related to customer satisfaction, the effectiveness of the measurement methods used to evaluate service performance is the primary concern for numerous enterprises. This study replaced the concept of the number of customer complaints used in previous studies with the time interval of customer complaints, and proposed a new service performance index. Because this index must be obtained through sample estimation, the result may be influenced by sampling errors, or a wrong conclusion may even occur. Considering the sampling error, this study ascertained the uniformly minimum variance unbiased estimators (UMVUE) of the service performance index, and used it to develop a reliable testing process for service performance. This method may be used as a reference for the service industry to assess whether the performance of a certain service item and the overall performance of an enterprise meet a standard level.

Usage behavior causal model construction for B&B-owned websites - from the B&B owner/operator perspective.

Previous studies on B&B (Bed and Breakfast) website usage behavior focused mainly on clients. It has been seldom researched to apply the Technology Acceptance Model (TAM) to verify the owner/operator usage behavior on B&B websites. This study aims to validate the causal relationship among beliefs, usage attitude, and behavior intention in website usage of B&B owners/operators. The results revealed that the TAM was recognized and the perceived ease of usage of B&B websites plays the most important role on the behavioral intention of B&B owners/operators. An easy and effective B&B website may allow an owner/operator to improve a B&B’s operational performance. Age has a significantly negative influence on perceived ease of use for B&B websites and educational attainment has a positive impact on perceived ease of use for B&B websites. Finally, conclusions and implications were discussed. This study can be used as a theoretical foundation and reference for further exploring related issues.