Ming-Hsien Caleb Li

Data envelopment analysis approaches for solving the multiresponse problem in the taguchi method

Abstract This research proposes a procedure for solving the multiresponse problem in the Taguchi method utilizing two data envelopment analysis (DEA) approaches, including comparisons of efficiency between different systems (CEBDS) and bilateral comparisons. In this procedure, each experiment in Taguchis orthogonal array (OA) is treated as a decision-making unit (DMU) with the multiresponses as the inputs and outputs for all DMUs. For each factor of OA, the DMUs are divided into groups, each at the same factor level. Then, DMUs efficiency is separately evaluated by the CEBDS approach and the bilateral comparisons approach for each factor. The level efficiency, or the average of the efficiencies obtained by the CEBDS and the bilateral comparisons approaches for that factor level, is then used to determine the optimal factor levels for multiresponses. Three case studies are provided for illustration; in all, the proposed procedure provides the largest total anticipated improvements. Hence, it should be considered the most effective among all approaches applied in the case studies, including principal component analysis, DEA-based ranking approach, and others. In addition, the proposed procedure is more effective and requires less computational effort when the DMUs efficiency is evaluated by the bilateral comparisons approach instead of the CEBDS approach. In conclusion, the proposed procedure will provide great assistance to practitioners for solving the multiresponse problems in manufacturing applications on the Taguchi method.

Factors influencing the repurchase intention and customer satisfaction: a case of Jordanian telecom companies

Todays harsh competition has forced telecom companies to continually enhance customer satisfaction, which leads to repurchases intention and consequently larger market share. Determination the key success factors in gaining competitive advantage within telecom industry has received significant research attention in different countries. This research examines the relationships between service quality, customer satisfaction, corporate image, perceived value, perceived price, loyalty, trust and checking their effects on repurchase intentions in Jordanian telecom companies using structural equation modelling. A structural model of 20 hypotheses is built. The data was collected from 550 users of telecom service. Results reveal that customer satisfaction is positively affected by service quality, perceived value, perceived price and image. Moreover, repurchases intention is positively affected by customer satisfaction, loyalty and perceived value. In conclusion, customer satisfaction is the key factor to be considered if telecom companies are willing to survive in todays harsh competition.

Optimizing the Performance of Plastic Injection Molding Using Weighted Additive Model in Goal Programming

Injection molding process is increasingly more significant in todays plastic production industries because it provides high-quality product, short product cycles, and light weight. This research optimizes the performance of this process with three main quality responses: defect count, cycle time, and spoon weight, using the weighted additive goal programming model. The three quality responses and process factors are described by appropriate membership functions. The Taguchis orthogonal array is then utilized to provide experimental layout. A linear optimization based on the weighted additive model in goal programming model is built to minimize the deviations of the product/process targets from their corresponding imprecise fuzzy values specified by the process engineers preferences. The results show that the average defect count is reduced from an average of 0.75 to 0.16. Moreover, the average cycle time becomes 13.06 seconds, which is significantly smaller than that obtained at initial factor settings = 15.10 seconds. Finally, the average spoon weight is exactly on its target value of 2.0 gm.

Solving dynamic systems with multi-responses by integrating desirability function and data envelopment analysis

Today’s complexity of product design requires improving multiple quality characteristics. This research proposes an approach that integrates the desirability function and data envelopment analysis to enhance process performance with dynamic multi-responses. Firstly, the desirability function is employed. Then, data envelopment analysis is used to obtain the best settings of controllable factor levels that make the effect of noise factors as small as possible. Three case studies are utilized to demonstrate the effectiveness of the proposed approach, in all of which the proposed approach is found an effective procedure in reducing the effect of noise factors, does not need huge data for the analysis or any subjective information and human judgment, and can be used regardless of linearity or nonlinearity relationship between the signal factor and responses. Such advantages should provide great assistance to product engineers in improving performance of dynamic systems with multiple responses.

The alpha error of the Taguchi method with L16 array for the LTB response variable using simulation

Taguchis quality engineering concepts are of great importance in designing and improving product quality and process. However, most of the controversy and mystique have been centred on Taguchis tactics. This research proposes an extension to the on-going research by investigating the probability of identifying insignificant factors as significant, or the so-called alpha error, with L16 orthogonal array for the larger-the-better type response variable using simulation. The response variables in the L16 array are generated from a normal distribution with the same mean and standard deviation. Consequently, the null hypothesis that all factors in the L16 array will be identified as insignificant is true. Simulation results, however, reveal that some insignificant factors are wrongly identified as significant with a very high probability, which may provide a risky parameter design. Therefore, efficient and more valid statistical tactics should be developed put out Taguchis important quality engineering concepts into practice.

Simulation and ABC to Improve the Performance of Emergency Department

This study aims at developing an Activity Based Costing ABC for the Emergency Department ED in a Jordanian hospital to determine associated costs and clarifies the financial practices inside ED rooms. For this purpose, simulation model is built for patients at the current ED activities and determine the costs for each room in ED. The total costs JD, number of served patients, and profits JD are 263562, 10256, and 146677, respectively. Improvement is suggested by studying three three-level controllable factors using simulation. It is noted that focusing on the lowest total costs, B-1 adding two beds with one added nurse and B-2 introducing four beds with two added nurses provide the two smallest total costs JD of 252568 and 253320, respectively. Whereas, for the largest number of served patients is achieved by A-1 assigning one sharing doctor for Abdominal and C-1 adding another room for abdominal with new doctor of equal number of served patients of 10466. In order to combine these two performance measures, the profit associated with each scenario is considered. It is found that factor A-1 provides the largest profit = 150,390 JD. The results of this research may provide decision makers valuable cost information that helps them in improving ED performance.

Alpha mistake of Taguchi method with L18 array for STB type QCH using simulation

The alpha mistake of Taguchi method is investigated for the smaller-the-better type quality characteristic with L18 (21 × 37) array using simulation. The results showed that the Taguchi method might result in identifying incorrectly some insignificant factors as significant. In conclusion, Taguchis quality engineering concepts are valuable, but his statistical tools, including: signal-to-noise ratio, testing at F value of four and pooling-up techniques, are found inefficient tools for robust design.