Applying the Weighting Methods in Importance-Performance Analysis to Evaluate the Service Quality - Case Studies of Service Industries around the Campus

ASIAIR > College of Computer Science > Department of Applied Informatics and Multimedia > Theses & dissertations > Item 310904400/3875

Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/3875

Title:	Applying the Weighting Methods in Importance-Performance Analysis to Evaluate the Service Quality - Case Studies of Service Industries around the Campus
Authors:	Sanky Yang
Contributors:	Department of Information Science and Applications
Keywords:	Service Quality;Importance- Performance Analysis;Weighting Methods;Kappa Test
Date:	2008
Issue Date:	2009-11-17 11:54:23 (UTC+0)
Publisher:	Asia University
Abstract:	This study has two main parts. The first one is the descriptive statistics of basic information, which focus on the service industries around the campus. This part can provide a deep understanding about customers to the business management of such a particular industry. Moreover, through applying the traditional Importance- Performance Analysis (IPA), the major strengths can be found and maintained, the major weaknesses can be specifically improved and then the quality of service will be enhanced. Originally, the traditional IPA must equip with the importance information. If not, the importance information can be derived by weighting methods. Conceptually, the second part is to implement IPA method with the derived importance from a variety of weighting methods. There are eight weighting methods introduced in our study, namely variance weighted method, sensitivity weighted method, entropy weighted method, coefficient of variation weighted method, correlation coefficient weighted method, certainty weighted method, Gini?Simpson index (GSI) weighted method and mutual information weighted method. Furthermore, case studies are provided. The result for each weighting method is compared one another along with that of traditional IPA. Percent rate and Kappa test are the two indicators to measure the consistency among eight weighted methods and the traditional IPA. Specifically, the Box plot is used to measure the stability in a variety of scenarios of IPA. The results of this study show several essential points. By using the traditional IPA in convenient stores, findings the keys to gain advantage are the shelf stands, store tidiness, attitude and politeness of the clerks. The neat and placing of shelf stands, freshness of goods, speed of restock, completeness of equipment and prices are the issues needed to be made better immediately. The response of dormitory manager, crisis handling, relationship and respect of residence are the essential advantage required to be maintained. On the other hand, facilities, improving and repairing are the problems have to be solved as soon as possible. In the field of library, its preserved key advantages are the service of librarians as well as the library itself, response, facilities and environment. Thus, the collection of library, seats, and computers in information search area are vital parts should be upgraded instantly. The conclusion of comparing the consistency between the result of each IPA method with the importance computed from each weighted method and that of traditional IPA is as following: there are five weighted methods are suggested when the overall satisfaction is unavailable, such as variance weighted method, entropy weighted method, coefficient of variation weighted method, certainty weighted method and Gina?Simpson index (GSI) weighted method. From the consistency and stability criteria, the analyzing result is that certainty weighted method is most recommended for implementing IPA method when the overall satisfaction is unavailable; there are three weighted methods are suggested when the overall satisfaction is available, which are sensitivity weighted method, correlation coefficient weighted method and mutual information. Among them, the result of IPA method with the importance computed from mutual information weighted method is much similar to that of traditional IPA.
Appears in Collections:	[Department of Applied Informatics and Multimedia] Theses & dissertations

Files in This Item:

File	Size	Format
	0Kb	Unknown	701	View/Open

Loading...