Mathematical Problems in Engineering

Mathematical Problems in Engineering / 2014 / Article
Special Issue

Mathematical and Computational Topics in Design Studies

View this Special Issue

Research Article | Open Access

Volume 2014 |Article ID 390878 | 8 pages |

Explore the Most Potential Supplier’s Selection Determinants in Modern Supply Chain Management

Academic Editor: Teen-Hang Meen
Received14 Jun 2014
Accepted31 Jul 2014
Published28 Aug 2014


To increment the research reliability, validity, and representativeness, this study creatively cross-employed the factor analysis (FA) and the grey relational analysis (GRA) methods. The results of the 144 fully completed questionnaires are analyzed by FA and then these results were utilized in second questionnaires design of 15 experts. Furthermore, the results of these second questionnaires were further analyzed by GRA in order to explore the most potential supplier’s selection determinants in the modern supply chain management (MSCM). Beyond a series of measurements, the measured results have induced three contributive findings: (1) the empirical interviewed industrialists reported concern that suppliers have to provide a higher material yield rate and material delivery on time rate for the qualitative increment as well as a higher supplier’s gross margin ROI for the financial stabilization in MSCM; (2) the 15 experts concluded that material insurance rate is an important attribute to estimate risky assessments and the supplier’s gross margin ROI and warehouse operations cost as a percentage of sales are critical elements in the financial evaluations of potential suppliers; and (3) Supplier’s gross margin ROI, outbound freight cost as a percentage of sales, and material insurance rate are the three most decisive determinants in MSCM.

1. Introduction

Nowadays, with reference to the increased complexity in manufacture processes, some serious issues (such as delivery speed, delivery reliability, customer service, labor productivity, capacity utilization, inventory turnover, procurement costs, procurement lead time, manufacture overhead costs, product volume flexibility, production mix flexibility, manufacturing process, conformance, and product quality) have constantly appeared and then existed in each procedure of supply chain because of the two specific characteristics of supply chain management (SCM): SCM is to manage each process and activity in supply chain from material purchasing, production manufacturing, product marketing and distribution, and financial reception [15]. As for the essential concept of SCM, [6] it clearly defined the terms of supply chains between material suppliers and manufacturing enterprises by means of business transaction structure and assessable scopes between each other [7]. Further indicated that the relationship and network of supply chains have been existed in downstream activity from materials transaction to finished goods or services to the end-user and these processes consist of supplier transaction, manufacture process, delivery process and final client transaction, according to the three major characteristics: demand, value-adding transformation, and supply information. Continuously, [8] pointed out the four fundamental supply chain hierarchies: supply within the firm boundaries, supply in a dyadic relationship, supply in an interorganizational chain, and supply in an interorganizational network. Specifically, after the globally financial crisis, the cash-flow stress without orders and account receivable stress with slow client-payment have already become the two crucial problems in SCM. Significantly, [9] creatively addressed the academic concept of financial influences from finance outlook on the patterns delivering the six comprehensive assessable criteria: financial forecasting, sales predicting, inventory strategies, delivery, supply’s structure, and customer service. For this reason, the essentially functional purpose of MSCM is to effectively and efficiently stabilize the material quality and quantity of manufacturing suppliers. However, due to the rapid development of manufacturing technology and globalized society, more and more issues have commenced to appear in four dimensions [10]: the modern supply chain management (MSCM); evaluated factors in inventory procedure (EFIP); evaluated factors in transaction-oriented procedure (EFTP); and evaluated factors in customer service procedure (EFCS). In fact, a plurality of manufacture enterprises companies has commenced to face many diversified influences in MSCM under uncertain but dynamic business environment. Thus, what is the efficient and effective approach to find out the best suppliers with the less negative influence and what are the most important assessable criteria to measure suppliers have become the most crucial problem in MSCM. However, beyond making a comprehensive survey of relative literatures in MSCM fields [1113], a lot of researches have paid numerous attentions on the production manufacture processes and human resource conduction in order to pursue the highest quality of products. Furthermore, there are a few studies to focus on the decisive influence of the potential determinants in modern SCM by means of the consolidated surveys of corporate SCM employees and the academic, corporate, and industrial experts. For this reason, this research cross-employs the analytical factor analysis (FA) and appraised grey cluster analysis (GCA) methods in order to discover the most potential supplier’s selection determinants in the modern supply chain management (“MSCM”) in order to maximize the corporate manufacturing performance and managerial profits. Therefore four brief elements in research framework are going to be conducted in this research and these are defining; integrating; developing; and conducting as described in Figure 1.

2. Relative Literatures

As for the comprehensive analysis of financial influences in SCM, there are twenty-one critical factors of the four issue dimensions in MSCM and these are EFMP issue dimension [14]: in order to recognize the quality of materials purchased from the suppliers’ and the nine crucial material factors of production suppliers have to be assayed in this assessable dimension. Significantly, these are supplier’s revenue growth rate (SRGR), supplier’s gross margin ROI (SGMROI), supplier’s sale forecast accuracy (SSFA), material yield rate (MYR), material returned rate (MRR), material delivery on time rate (MDOTR), material inspection yield rate (MIYR), material insurance rate (MIR) [15]; and material order fill rate (MOFR) [16]; EFIP issue dimension [17]: in order to realize the inventory system, there are the four critical factors to be considered in this analytical dimension: inventory turns rate (ITR), obsolete inventory rate (OIR), inventory accuracy rate (IAR); and material inventory warehouse management rate (MIWMR); EFTP issue dimension [18]: in order to the stabilization of material suppliers’ operation system, the five chief financial factors are explored in this dimension and these are warehouse operations cost as a percentage of sales (WOCSP), outbound freight cost as a percentage of sales (OFCOSP), product on-time shipment (POTS), material web-oriented transaction rate (MWT) [19]; and material electronic data interchange transaction rate (MEDIR) and EFCS issue dimension [20, 21]: in order to completely understand the situation of conducting the customer feedback of suppliers, the three basic evaluated attributes are considered in this dimension: supplier’s customer complaint rate (SCCR) [22], supplier’s customer satisfaction rate (SCSR) [23], and supplier’s customer service response time (SCSPT) [24].

Continuously, in order to completely reflect the comment of the interviewed participants’ comments of SCM corporate employees on the empirically cross-analyses, this research adapted the principal component analysis of FA approach because it is able to evaluate correlation coefficient among each assessable variable in order to acquire communality between each common factor in the higher relatively analytical dimensions. Subsequently, [25, 26] pointed out that the analytical dimension of FA consists of two principle elements (such as common factor (or latent factor) and unique factor) resulted in two typical factor analyses (such as exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) in FA approach). Particularly, [27] created the principle component analysis (PCA) [28] and principal axis factors analysis (PAFA) into FA approach to prompt two similarities of problems in FA: the variable is same with two groups (e.g., the same set of measures might be taken on men and women or on treatment and control groups and then the question arises whether the two factor structures are the same) and sets of variable in the one group (e.g., two test batteries might be given to a single group of subjects and questions asked about how the two sets of scores differ. Or the same battery might be given under two different conditions). Consequently, [28] addressed the typical measurement statistics process of FA approach in

As for the research validity, [29] induced the Kaiser-Meyer-Olkin measure of sampling adequacy (KMOMSA) of Kaiser-Meyer-Olkin test in surveyed measures (such as questionnaire) to identify the potential communality among each assessable criterion. Continuously, the test number of KMOMSA is supposed to be from 0 to 1. Consequently, the test number of KMOMSA is more closed to 1 and there are more communalities between each assessable criterion which means the collected data is more suitable for FA approach as described in Table 1. In terms of the discussion of research reliability in FA approach, [30] induced that the examined numbers (Cronbach’s alpha, Cronbach α) of each assessable criterion in Likert’s scales are able to present the stability of each assessable criterion in analytical processes of FA approach as expressed in Table 2 [3134]. Currently, FA approach has been a mainstream in statistic measurements in diversified research fields in order to handle the complex analysis with complex factors [3538] because there are a lot of indirectly observed potential influenced factors in the discussion of mental philosophical researches. In particular, these potential factors are supposed to be organized to common influenced factors (oblique factors) or uncommon influence factors (orthogonal factors) and based on the patterns of linear combination of these organized common factors, the multilateral analyses are discussed around the research problems [39, 40].

Test number of KMOMSACollection data appropriation for FA

Up 0.9Extremely appropriated for FA approach
0.8-0.9Plentifully appropriated for FA approach
0.7-0.8Appropriated for FA approach
0.6-0.7Scarcely appropriated for FA approach
0.5-0.6Unappropriated for FA approach
Below 0.5Extremely unappropriated for FA approach

Cronbach’s Measured results

Extremely stable
Plentifully unstable
Possibly stable
Rarely stable
Extremely unstable

In order to truly understand the comments and messages from expert’s questionnaires, this study further applied GRA method to conduct the compared pair-wise weighted measurements of each twenty-one criterion of academic, industrial, and governmental experts. Hence, as for the initiation of GRA method, [41] pioneered GRA method of the grey system theory (GST) to assay the uncertain and fuzzy collection-data according to the concept of the Fuzzy Theory and GRA conceptual idea was that there are a series of dependences to be existed among each assessable criterion. Subsequently, the exact information of surveyed data are supposed to be grey system established between block system and white system, in order to integrate the indefinite research data to become useful research data which in-depth conduct managerial control, decision-making, and foreseeing research topic. The essential goal of GRA method of GST is to not only measure the level of relation between each appraised and affected factors under uncertain situations but to also use the tendency level among uncertain and incomplete information of each appraised and affected factor to quantify the level of relation in order to appraise the dependence or independence relations between each influenced factor in the three kinds of analytical goals [42, 43]:(1)the larger the better (, LTB);(2)the smaller the better (, STB);(3)the nominal the best (, NTB).Furthermore, the is computed variable of original data; the is measured variable of the data after GRA analysis; the is calculated variables of the minimum of original data and the is the measured variable of maximum of original data.

3. Empirical Measurements

3.1. First Research Step: FA Approach

In order to effectively increase the research reliability, the compared pairwise measure was utilized in the questionnaire scale of surveyed questionnaires and then the pairwise comparisons at two level are evaluated by means of the related interdependence and importance ranging from equal important to extreme important (9) that follows the concept of the Likert’s scale. Furthermore, the statistic description of 153 questionnaires was received, of which 144 were fully completed out of 250 questionnaires sent to corporate SCM employees by means of collected assistance from the Taiwan International Logistics & Supply Chain Association (TILSCO) through diversified collection manners including digital e-mail, documentary letter, and interview in person were illustrated in Table 3. Consequently, Table 4 points out that the general Cronbach’s Alpha (α) and standardized Cronbach’s alpha (α) of validity test results of the surveyed questionnaire were of 0.744 and 0.81, both higher than 0.7 which means the interviewed questions in questionnaire are valid. Subsequently, the overall questionnaire response rate was 61.2%. Continuously, the valid collected questionnaires were up to 144 questionnaires without any unclear answers in the compared pairwise questions of twenty-one assessable criteria and consequently, the valid questionnaires rate was 57.6%. Significantly, Table 5 presents the collection of entire 144 valid questionnaires which were suited for FA approach because that Kaiser-Meyer-Olkin Measure of Sampling Adequacy of KMOP-Bartlett test of 144 valid questionnaires was 0.715 which was located at the suitable range and the significance of the KMO and Bartlett test is 0.00000012 which was smaller than 0.01.

Questionnaire itemsQuestionnaire statistic description

GenderMale: 67.36% (97)
Female: 32.63% (47)

Working experienced years in SCM0-1 years: 27.08% (39)
2–5 years: 54.16% (78)
5–10 years: 13.19% (19)
Over 10 years: 5.57% (8)

EducationBachelor degree: 74.3% (107)
Master degree: 22.22% (32)
Doctoral degree: 3.48% (5)

Cronbach’s alpha ()Standardized Cronbach’s alpha ()Examined items


Kaiser-Meyer-Olkin measure of sampling adequacy0.715
Bartlett test of sphericity
 Approx. Chi-Square1000.879

Subsequently, Table 6 describes the significance of the analysis of variance (ANOVA) test of reliability examination of entire 144 valid questionnaires which was 0.00000023 which was smaller than 0.01 as well and, hence, there is higher research validity in FA analytical measurements of these 144 valid questionnaires. Consequently, the communal influenced loadings of each assessable criterion in communalities matrix of principal component analysis of FA approach were completely illustrated in Table 7. As a result, the most four top loadings were located at the most crucial evaluated factors: MYR (0.851), MDOTR (0.826), SGMROI (0.825), and OFCOSP (0.815) by means of principal component analysis of FA approach.

Sum of squaresDfMean sumSig.

Between groups520.2741433.638
Within groups

Average mean of total valid questionnaires is 5.8.

Evaluated criteriaInitialExtraction


Extraction method: Principal component analysis.
3.2. Second Research Step: GRA Method

In order to increase the research academic professionality and measured reliability, GRA method was further applied to deal with the second-hierarch fifteen expert’s questionnaires for distinctly discovering the true comments of the surveyed questionnaire of the interviewed experts without linguistic confusion. Therefore, [42] discovered that there are the least errors of validity and reliability in the Delphi method when collected questionnaires come from, at least, over 10 professional interviewees. In addition, this research utilized the Delphi method to gather questionnaires and comments from the second-level interviewed fifteen experts who 10 of which are organized from the three professional groups. The first group represents five academic scholars with at least 10 years of extensive research in relative SCM fields and the second group comprised of five industrially senior managers who have over 10 years of working experience in the correlative SCM industries. Significantly, the last groups consisted of five government officers who have been involved in governmental SCM policies for over 10 years. Continuously, the grey relation grades (GRG) of GRA method among each twenty-one assessable criterion were presented in Table 8. Consequently, GRA of each twenty-one assessable criterion were measured according to the grey equation and described in Table 9.

Academic scholarsEmpirical senior managersGovernment officers
12345 1 2 3 4 51 2 3 4 5 


Evaluated criteriaGRG


3.3. Third Research Step: Integrate FA Approach and GRA Method

In order to coordinate with first-level general and second-level expert’s survey questionnaires, each potential candidate has to match each assessable subcriterion matched in each evaluated criterion through pairwise compared matrixes. Hence, in order to reflect the comparative score for the three kinds of candidates in problem solving the research issue, (2) of the synthetically comparative index numbers (SCIN) is applied to compute the comprehensively comparative related priority weight   (eigenvector) in the matrix and the SCIN which is defined by where is the importance of related priority weight   (eigenvector) of the consolidated measurement of FA approach and GRA method for each assessable criterion ; is the importance of related priority weight   (eigenvector) of the statistic measurement of FA approach for each assessable criterion ; and is the importance of related priority weight   (eigenvector) of the statistic measurement of GRA method for each assessable criterion . Subsequently, the consolidated measurement matrix is demonstrated in Table 10 based on the consolidated measurements of FA approach and GRA methods. Consequently, the first highest evaluated score of the completed SCIN of 0.6057 is located in SGMROI column and the second and third highest scores of the complete SCIN of 0.5746 and 0.5517 are located in OFCOSP and MIR.

Communality loading (FA approach)FA rankingGrey relation grade (GRA method)GRA rankingSCINSCIN ranking


4. Conclusion

According to the swift development of manufacture technologies, there are a lot of crucial factors to affect the corporate supplier’s selection under the lowest risks and highest profits consideration. Hence, this study firstly employed FA approach to conduct the first-level 144 empirical questionnaires and then applied GRA method to assay the second-level 15 expert’s questionnaires in order to explore the most potential supplier’s selection determinants in MSCM due to the increment of the research reliability, validity, and representativeness. Significantly, after making a comprehensive survey of relative literatures as well as conducting a series of hierarchically evaluated measurements, the measured consequences have distinctly induced the three contributive findings: the empirical interviewed industrialists reported concern that suppliers have to provide not only a higher material yield rate (MYR) and material delivery on time rate (MDOTR) for the stably qualitative increment in MSCM but must also provide higher supplier’s gross margin ROI (SGMROI) for the financial stabilization in MSCM; the academic, corporate executive, and governmental experts concluded that material insurance rate (MIR) is an important attribute to estimate risky assessments of suppliers and the supplier’s gross margin ROI (SGMROI) and warehouse operations cost as a percentage of sales (WOCSP) are critical elements in the financial evaluations of potential suppliers and supplier’s gross margin ROI (SGMROI), outbound freight cost as a percentage of sales (OFCOSP), and material insurance rate (MIR) are the three most decisive determinants in MSCM by weighting the results from the two sets of questionnaires. According to the expert’s comments of surveyed questionnaire, the manufacturing enterprises have commenced to suffer the financial stress from not only suppliers but also customers after the 2008 global finance crisis because the suppliers are not willing to provide the stabilized material supply chain and the customers are not willing to offer a stable procurement demand orders or paying over six months check for these orders.

Conflict of Interests

The authors declare that there is no conflict of interests regarding the publication of this paper.


  1. E. Deutskens, K. de Ruyter, and M. Wetzels, “An assessment of equivalence between online and mail surveys in service research,” Journal of Service Research, vol. 8, no. 4, pp. 346–355, 2006. View at: Publisher Site | Google Scholar
  2. P. W. Balsmeier and W. J. Voisin, “Supply chain management: a time-based strategy,” Industrial Management, vol. 38, no. 5, pp. 24–27, 1996. View at: Google Scholar
  3. B. M. Beamon, “Supply chain design and analysis: models and methods,” International Journal of Production Economics, vol. 1, no. 4, pp. 281–294, 1998. View at: Google Scholar
  4. M. Christopher, Logistics and Supply Chain Management: Strategies for Reducing Costs and Improving Services, Pitman, London, UK, 1992.
  5. M. Christopher, Logistics and Supply Chain Management, Financial Times Pitman, London, UK, 2nd edition, 1998.
  6. M. C. Cooper and M. E. Lisa, “Characteristics of supply chain management and implication for purchasing and logistics strategy,” International Journal of Logistics Management, vol. 4, no. 2, pp. 21–58, 1993. View at: Google Scholar
  7. F. Chen, Z. Drezner, J. K. Ryan, and D. Simchi-Levi, “Quantifying the bullwhip effect in a simple supply chain: the impact of forecasting, lead times, and information,” Management Science, vol. 46, no. 3, pp. 436–443, 2000. View at: Google Scholar
  8. L. M. Ellram, W. L. Tate, and C. R. Carter, “Product-process-supply chain: an integrative approach to three-dimensional concurrent engineering,” International Journal of Physical Distribution and Logistics Management, vol. 37, no. 4, pp. 305–330, 2007. View at: Publisher Site | Google Scholar
  9. R. N. Kostoff and E. Geisler, “Strategic management and implementation of textual data mining in government organizations,” Technology Analysis and Strategic Management, vol. 11, no. 4, pp. 493–525, 1999. View at: Publisher Site | Google Scholar
  10. P. Lee, “The 5 keys to supply chain success,” CIO Magazine, 2001. View at: Google Scholar
  11. S. Croom, P. Romano, and M. Giannakis, “Supply chain management: an analytical framework for critical literature review,” European Journal of Purchasing and Supply Management, vol. 6, no. 1, pp. 67–83, 2000. View at: Publisher Site | Google Scholar
  12. L. Lapide, “What about measuring supply chain performance?” 2000. View at: Google Scholar
  13. R. Metters, “Quantifying the bullwhip effect in supply chains,” Journal of Operations Management, vol. 15, no. 2, pp. 89–100, 1997. View at: Google Scholar
  14. M. Christopher and H. Lee, “Mitigating supply chain risk through improved confidence,” International Journal of Physical Distribution & Logistics Management, vol. 34, no. 3, pp. 388–396, 2004. View at: Google Scholar
  15. A. Norrman and U. Jansson, “Ericsson's proactive supply chain risk management approach after a serious sub-supplier accident,” International Journal of Physical Distribution & Logistics Management, vol. 34, no. 3, pp. 434–456, 2004. View at: Google Scholar
  16. L. C. Giunipero and R. A. Eltantawy, “Securing the upstream supply chain: a risk management approach,” International Journal of Physical Distribution & Logistics Management, vol. 34, no. 2, pp. 698–713, 2004. View at: Google Scholar
  17. P. K. Oliver and M. D. Webber, “Supply-chain management: logistics catches up with strategy,” in Logistics: The Strategic Issues, M. Christopher, Ed., pp. 63–75, Outlook, Booz, Allen and Hamilton, Chapman Hall, London, UK, 1992. View at: Google Scholar
  18. P. C. Brewer and T. W. Speh, “Using the balanced scorecard to measure supply chain performance,” Journal of Business Logistic, vol. 21, no. 1, pp. 75–93, 2000. View at: Google Scholar
  19. D. L. Simchi, P. Kaminsky, and E. L. Simchi, Designing and Managing the Supply Chain, McGraw-Hill, Boston, Mass, USA, 2000.
  20. G. Zäpfel and B. Piekarz, Supply Chain Controlling, Überreuter, Vienna, Austria, 1996.
  21. K. B. Hendricks and V. R. Singhal, “What is the real cost of your supply chain problems?” Supply Chain & Logistics Journal, vol. 4, no. 4, pp. 1–42, 2001. View at: Google Scholar
  22. J. B. Hulihahn, “International supply chain management,” International Journal of Physical Distribution and Materials Management, vol. 15, no. 1, pp. 51–66, 1985. View at: Google Scholar
  23. B. J. LaLonde, “The costs of functional shiftability,” Supply Chain Management Review, pp. 9–10, 1998. View at: Google Scholar
  24. B. J. LaLonde and L. P. Terrance, “Issues in supply chain costing,” The International Journal of Logistics Management, vol. 7, no. 1, pp. 5–8, 1996. View at: Google Scholar
  25. H. H. Harman, Modern Factor Analysis, University of Chicago Press, 1976. View at: MathSciNet
  26. W. F. Velicer, “Determining the number of components from the matrix of partial correlations,” Psychometrika, vol. 41, no. 3, pp. 321–327, 1976. View at: Publisher Site | Google Scholar | Zentralblatt MATH
  27. R. B. Darlington, Factor Analysis, 2004.
  28. J. D. Brown, Principal Components Analysis and Exploratory Factor Analysis—Definitions, Differences and Choices, JALT Testing & Evaluation SIG Newsletter, Shiken, China, 2012.
  29. H. F. Kaiser, “An index of factorial simplicity,” Psychometrika, vol. 39, no. 1, pp. 31–36, 1974. View at: Publisher Site | Google Scholar | Zentralblatt MATH
  30. L. J. Cronbach, “Coefficient α and the internal structure of tests,” Psychometrika, vol. 16, no. 3, pp. 297–334, 1951. View at: Publisher Site | Google Scholar
  31. N. Schmitt, “Uses and abuses of coefficient alpha,” Psychological Assessment, vol. 8, no. 4, pp. 350–353, 1996. View at: Google Scholar
  32. R. Zinbarg, I. Yovel, W. Revelle, and R. McDonald, “Estimating generalizability to a universe of indicators that all have an attribute in common: a comparison of estimators for alpha,” Applied Psychological Measurement, vol. 30, pp. 121–144, 2006. View at: Google Scholar
  33. W. Revelle and R. E. Zinbarg, “Coefficients alpha, beta, omega, and the glb: comments on Sijtsma,” Psychometrika, vol. 74, no. 1, pp. 145–154, 2009. View at: Publisher Site | Google Scholar | Zentralblatt MATH | MathSciNet
  34. N. Ritter, “Understanding a widely misunderstood statistic: Cronbach's alpha,” in Proceeding of the Southwestern Educational Research Association (SERA) Conference, New Orleans, La, USA, 2010. View at: Google Scholar
  35. D. Love, D. K. Hallbauer, A. Amos, and R. K. Hranova, “Factor analysis as a tool in groundwater quality management: two southern African case studies,” Physics and Chemistry of the Earth, vol. 29, no. 15–18, pp. 1135–1143, 2004. View at: Publisher Site | Google Scholar
  36. J. Ruscio and B. Roche, “Determining the number of factors to retain in an exploratory factor analysis using comparison data of known factorial structure,” Psychological Assessment, vol. 24, no. 2, pp. 282–292, 2012. View at: Publisher Site | Google Scholar
  37. L. E. Garrido, F. J. Abad, and V. Ponsoda, “A new look at Horn’s parallel analysis with ordinal variables,” Psychological Methods, vol. 18, no. 4, pp. 454–474, 2013. View at: Publisher Site | Google Scholar
  38. N. Ritter, “A comparison of distribution-free and non-distribution free methods in factor analysis,” in Proceedings of the Southwestern Educational Research Association (SERA) Conference, ED529153, New Orleans, Lo, USA, 2012. View at: Google Scholar
  39. M. G. R. Courtney, “Determining the number of factors to retain in EFA: using the SPSS R-Menu v2.0 to make more judicious estimations,” Practical Assessment, Research and Evaluation, vol. 18, no. 8, pp. 24–57, 2013. View at: Google Scholar
  40. R. T. Warne and R. Larsen, “Evaluating a proposed modification of the Guttman rule for determining the number of factors in an exploratory factor analysis,” Psychological Test and Assessment Modeling, vol. 56, pp. 104–123, 2014. View at: Google Scholar
  41. D. Ju-Long, “Control problems of grey systems,” Systems & Control Letters, vol. 1, no. 5, pp. 288–294, 1982. View at: Publisher Site | Google Scholar
  42. J. Deng, “Introduction to grey system theory,” Journal of Grey System, vol. 1, pp. 1–24, 1989. View at: Google Scholar
  43. J. W. K. Chan and T. K. L. Tong, “Multi-criteria material selections and end-of-life product strategy: grey relational analysis approach,” Materials and Design, vol. 28, no. 5, pp. 1539–1546, 2007. View at: Publisher Site | Google Scholar

Copyright © 2014 Ming-Yuan Hsieh et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

1042 Views | 514 Downloads | 2 Citations
 PDF  Download Citation  Citation
 Download other formatsMore
 Order printed copiesOrder

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19.