Yapısal Denklemlere Yönelik Üç Ana Yaklaşımın Karşılaştırılması

Year 2023, Volume: 1 Issue: 1, 44 - 55, 23.03.2023

Aslı Gül Öncel , Mariem Khadhraoui

Abstract

Yıllar içerisinde, bilimsel araştırma daha karmaşık hale gelmiş ve artık sadece iki değişken arasındaki ilişkiyi doğrulamayı değil, bir dizi ilişkiyi incelemeyi amaçlamaktadır. Bu nedenle de, istatistiksel yöntemler uyarlanmıştır. Bu araştırmanın amacı, bir dizi eşzamanlı karşılıklı ilişkiyi açıklamak için çeşitli istatistikleri birleştiren ve böylece araştırmacıların olayları açıklama yeteneğini geliştiren, çoklu regresyondan türetilen en gelişmiş çok değişkenli analiz tekniklerini sunmaktır; çoklu regresyona dayalı PLS (kısmi en küçük kare) ve LISREL'in yapısal eşitlik modelleme sistemi LISREL (Linear Structural Relationships) (AMOS, SPSS IBM'in versiyonudur) LISREL'dir. Bu makale iki yaklaşımı ve bunların avantaj ve dezavantajlarını sunmaktadır. PLS, keşif araştırması için daha uygun olurken, LISREL doğrulayıcı araştırma için daha iyi olacaktır. Okuyucu, bilimsel belgelerde belirtildiği gibi, iki yaklaşım arasındaki temel farkları, izlenen hedeflere, veri miktarına ve diğer faktörlere bağlı olarak avantaj ve dezavantajlarını bulacaktır. Bu yöntemleri destekleyen yazılımların her birinin de hızla geliştiğinin eklenmesi gerekir.

Keywords

Modelleme yaklaşımı, PLS, LISREL, AMOS

Consideration of the factors of choice between PLS and LISREL

Abstract

Over the years, scientific research has become more sophisticated and no longer aims to simply verify a relationship between two variables but rather aims to examine a range of relationships. This is why statistical methods have adapted. The objective of this research is to present state-of-the-art multivariate analysis techniques, derived from multiple regression, that combine various statistics to account for a set of simultaneous interrelationships, thereby improving the ability researchers to explain phenomena; it is PLS (partial least square), based on multiple regression and LISREL the structural equation modeling system LISREL (Linear Structural Relationships) (AMOS being the version of SPSS IBM) of LISREL. This article presents the two approaches and their advantages and disadvantages. PLS would be better suited for exploratory research while LISREL would be better for confirmatory research. The reader will find the main differences between the two approaches, their advantages and disadvantages depending on the objectives pursued, the amount of data and other factors, as mentioned in the scientific documentation. Let us add that each of the software incarnations of software supporting these methods evolves rapidly.

Keywords

Modeling approach, PLS, LISREL, AMOS

Une Comparaison entre trois des Principales Approches d'Equations Structurelles

Abstract

Au fil des ans, la recherche scientifique s’est sophistiquée et ne vise plus la simple vérification d’une relation entre deux variables mais vise plutôt l’examen d’un ensemble de relations entre plusieurs variables. C’est pourquoi les méthodes statistiques se sont également adaptées. L'objectif de cette recherche est de présenter des techniques d’analyse multivariée, dérivées de la régression multiple qui combinent de diverses statistiques pour rendre compte d’un ensemble d’interrelations simultanées, améliorant ainsi la capacité des chercheurs à expliquer des phénomènes; il s’agit de moindres carrés partiels- PLS (Partial Least Square), d’analyse des structures de moment- AMOS (Analysis of Moment Structures) et de système de modélisation d’équations structurelles- LISREL (Linear Structural Relationships). Ces deux derniers se basent sur l’analyse de Covariance. Cet article présente trois des principales approches ainsi que leurs avantages et inconvénients. PLS conviendrait mieux à la recherche exploratoire alors que LISREL et AMOS seraient plus préférables pour la recherche confirmatoire. Le lecteur trouvera les principales différences entre trois approches, leur avantages et aussi bien leurs inconvénients en fonction des objectifs poursuivis de la quantité de données et d’autres facteurs tels que mentionnés dans la documentation scientifique. Ajoutons que chacune des incarnations logicielles supportant ces méthodes évoluent rapidement.

Keywords

Approche de modélisation, PLS, LISREL, AMOS

References

• Adila, T. M., Bintang, W. S., Ikhsan, R. B., & Fahlevi, M. (2020). Instagram as Information In Developing Purchase Intentions: The Role Of Social E-Wom And Brand Attitude. In 2020 International Conference on Information Management and Technology (ICIMTech) (pp. 427-431). IEEE. https://doi.org/10.1109/ICIMTech50083.2020.9211151
• Amt.G., Lindstädt H. & Wolff M. (2008). Standardized strategy assessment as a contribution to banks' corporate ratings. Investment Management and Financial Innovations, 5(3), 44-50.
• Bacon, L. D. (1999). Using LISREL and PLS to measure customer satisfaction. In Sawtooth Software Conference Proceedings, La Jolla, California, Feb., 2-5.
• Bentler, P. M., & Bonett, D. G. (1980). Significance tests and goodness-of-fit in the analysis of covariance structures. Psychological Bulletin, 88, 588–600. https://doi.org/10.1037/0033-2909.88.3.588
• Blalock, H. M. (1961). Correlation and causality: The multivariate case. Social Forces, 39, 246–251. https://doi.org/10.2307/2573216
• Bouncken, R. B., Pesch, R., & Gudergan, S. P. (2015). Strategic embeddedness of modularity in alliances: Innovation and performance implications. Journal of Business Research, 68(7), 1388-1394. https://doi.org/10.1016/j.jbusres.2015.01.020
• Chau, P. Y. (1997). Reexamining a model for evaluating information center success using a structural equation modeling approach. Decision Sciences, 28(2), 309-334. https://doi.org/10.1111/j.1540-5915.1997.tb01313.x
• Chin W. W. (1995). Partial least squares is to LISREL as principal components analysis is to common factor analysis. Technology Studies, 2(2), 315-319.
• Chuang, S. H., & Lin, H. N. (2017). Performance implications of information-value offering in e-service systems: Examining the resource-based perspective and innovation strategy. The Journal of Strategic Information Systems, 26(1), 22-38. http://dx.doi.org/10.1016/j.jsis.2016.09.001
• Duncan, O. D. (1966). Path analysis: Sociological examples. American Journal of Sociology, 74, 119–137. https://doi.org/10.1086/224256
• Duncan, T. E., Duncan, S. C., Strycker, L. A., Li, F., & Alpert, A. (1999). An introduction to latent variable growth curve modeling: Concepts, issues, and applications. Mahwah, NJ: Erlbaum. https://doi.org/10.1016/S0005-7894(04)80042-X
• Fairuzzahira, F., Zagloel, T. Y., & Ardi, R. (2020). Conceptual Modelling of Supplier Loyalty and Buyer-Supplier Relationship for Mediation: A Case Study in Plywood Industry. In Proceedings of the 3rd Asia Pacific Conference on Research in Industrial and Systems Engineering, (pp. 295-299). https://doi.org/10.1145/3400934.3400988
• Frichi, Y., Jawab, F., & Boutahari, S. (2019). SEM to analyze the interaction between hospital logistics and quality of care, a systematic review. In 2019 International Colloquium on Logistics and Supply Chain Management (LOGISTIQUA) (pp. 1-5). IEEE. https://doi.org/10.1016/j.omega.2018.01.007
• Fornell C, & Bookstein FL. (1982). Two structural equation models: LISREL and PLS applied to consumer exit-voice theory. Journal of Marketing Research, 1, 440-452. https://doi.org/10.2307/3151718
• Gefen, D., Straub, D. W., & Boudreau, M.C. (2000). Structural Equation Modeling Techniques and Regression: Guidelines For Research Practice. Communications of AIS, 4 (7), 1-79.
• Goodhue, D., Lewis, W., & Thompson, R. (2006, January). PLS, small sample size, and statistical power in MIS research. In System Sciences, 2006. HICSS'06. Proceedings of the 39th Annual Hawaii International Conference, Vol. 8, 202b-202, IEEE.
• Goodhue D.L,Lewis W.,Thompson R. (2012). Research note: Does PLS have advantages for small sample size or non-normal data? MIS Quaterly, 36(3), 981-1001. https://doi.org/10.2307/41703490
• Hair J.F, Thomas G., Hult M., Ringle C.M., Sarstedt M. (2016). A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM), Sage publications.
• Hasanabadizadeh, N., Omidi-Najafabadi, M., Mirdamadi, S. M., & Lashgarara, F. (2019). An agricultural micro-insurance development model for rural areas of Iran. EurAsian Journal of BioSciences, 13(2), 2071-2077.
• Hmimou, A. (2021). On the Comparison Between LISREL and PLS-PM in Structural Equation Modeling. In International Conference on Research in Applied Mathematics and Computer Science, Vol. 2021, ICRAMCS 2020.
• Hulland, J. (1999). "Use of partial least squares (PLS) in strategic management research: A review of four recent studies." Strategic Management Journal, 20(2), 195-204. https://doi.org/10.1002/(SICI)1097-0266(199902)20:2<195::AID-SMJ13>3.0.CO;2-7
• Idowu, A., Nat, M., & Kissi, P. S. (2020) Student perception of usefulness and ease using Kahoot, a free web-based tool in a tertiary education setting." Acta Scientiarum. Technology, http://periodicos.uem.br/ojs ISSN on-line: 1807-8664 Doi: 10.4025/actascitechnol.v43i1.47347, 1-12. https://doi.org/10.4025/actascitechnol.v42i1.47347
• Joreskog, K. G., & Surbom, D. (1981). WSREL: Analysis of linear structural relationships by maximum likelihood and least squares methods. Chicago: National Educational Resources. Kline, Rex.B. (2019). Principles and Practices of Structural Equation Modeling, Fourth Edition. New York : The Guilford Press.
• Malik, M. (2020). A Review of empirical research on Internet & Mobile banking in developing countries using UTAUT Model during the period 2015 to April 2020. Journal of Internet Banking and Commerce, 25(2), 1-22.
• Næs, T., Romano, R., Tomic, O., Måge, I., Smilde, A., & Liland, K. H. (2020). Sequential and orthogonalized PLS (SO‐PLS) regression for path analysis: Order of blocks and relations between effects. Journal of Chemometrics,Wiley, 35(4), 1-24. https://doi.org/10.1002/cem.3243
• Nam, S. T., Kim, D. G., & Jin, C. Y. (2018). A Comparison Analysis among Structural Equation Modeling (AMOS, LISREL and PLS) Using the Same Data. Journal of the Korea Institute of Information and Communication Engineering, 22(7), 978-984. http://dx.doi.org/10.6109/jkiice.2018.22.7.978
• Pantai, K. L. (2012). PLS Path Model for Testing the Moderating Effects in the Relationships among Formative IS Usage Variables of Academic Digital Libraries. Australian Journal of Basic and Applied Sciences, 6(7), 365-374.
• Qiu, L., & Qi, L. (2020). E-learning assessment for tourism education LISREL assisted intercultural tourism perception and data integrated satisfaction perspectives. Journal of Computing in Higher Education, 32(1), 89-108.
• Romano, R., Tomic, O., Liland, K. H., Smilde, A., & Næs, T. (2019). A comparison of two PLS‐based approaches to structural equation modeling. Journal of Chemometrics, 33(3), 1-28. https://doi.org/10.1002/cem.3105
• Schumaker, R. E., & Marcoulides, G. A. (Eds.). (1998). Interaction and nonlinear effects in structural equation modeling. Mahwah, NJ: Erlbaum.
• Spearman, C. (1904). General intelligence, objectively determined and measured. The American Journal of Psychology,University of Illinois Press, 15(2), 201–292.
• Tenenhaus, M., Amato, S., & Esposito Vinzi, V. (2004). A global goodness-of-fit index for PLS structural equation modelling. In Proceedings of the XLII SIS scientific meeting, Vol. 1, 739-742.
• Wolfle, L. M. (2003). The introduction of path analysis to the social sciences, and some emergent themes: An annotated bibliography. Structural Equation Modeling, 10, 1–34. https://doi.org/10.1207/S15328007SEM1001_1
• Wright, S. (1921). Correlation and causation. Journal of Agricultural Research, 20, 557–585.
• Wright, S. (1934). The method of path coefficients. Annals of Mathematical Statistics, 5, 161–215. https://doi.org/10.1214/aoms/1177732676
• Wold, H. (1982). Soft modeling: The basic design and some extensions. Wold (Eds.), Systems under indirect observation. Amsterdam, The Netherlands: North Holland.