Development of A Structural Model with Multicollinearity and Outliers Problems

Pembangunan Model Berstruktur Bermasalah Multikolinearan dan Data Pencilan

Authors

  • Zulkifley Mohamed
  • Rozie Rosli

Keywords:

Structural Equation Model, Partial Lesat Squares, Robust Variance, Academic Performance Structural Model

Abstract

Structural Equation Model (SEM) based on a Partial Least Squares (PLS) method is amongthe best methods used to develop educational models involving structural relationshipof some latent variables. Despite the important role that PLS has played in developingeducational models, few attempts have been made to modify the method of its estimation.This paper describes the development of an education model by using the modified methodin estimating the parameter’s model, namely Robust PLS. This study improved the methodfor estimating the latent variables through the use of robust variance. The new modifiedmethod attempted to solve two main problems in modeling namely multicollinearity andoutliers. To test the effectiveness of Robust PLS, the academic performance model basedon Robust PLS and Conventional PLS were compared. The study revealed that the SEMbased on Robust PLS (Robust SEM-PLS) is better than SEM based on ConventionalPLS (Conventional SEM-PLS) when the problems of multicollinearity and outlier in the developed model exist.

Downloads

Download data is not yet available.

References

Aida Baharuddin (2004). Hubungan Antara Faktor Sosioekonomi dan Persekitaran Keluarga Terhadap Sikap Dan Pencapaian Matematik Pelajar Tingkatan 4 Sekolah Menengah Kebangsaan Keroh, Kuala Krai, Kelantan. (Tesis yang tidak diterbitkan). Fakulti Sains dan Matematik, Universiti Pendidikan Sultan Idris.

Akter, S., D’Ambra, J. & Ray, P. (2011). An Evaluation of PLS Based Complex Models: The Roles of Power Analysis, Predictive Relevance and GoF index. AMCIS2011, 1-7. Detroit: Association for Information Systems.

Asnul Dahar Minghat, & Anasyuhada La’anain (2007). Faktor-Faktor yang Mempengaruhi Kecemerlangan dalam Pencapaian Akademik Pelajar-Pelajar Tahun Empat Ijazah Sarjana Muda Teknologi Serta Pendidikan (Kejuruteraan Awam, Elektrik, Mekanikal) di Fakulti Pendidikan, UTM. (Tesis yang tidak diterbitkan). Fakulti Pendidikan, Universiti Teknologi Malaysia.

Azrul Mahfurdz, & Saifuddin Semail (2011). Hubungan Gaya Pembelajaran, Motivasi & Pencapaian Pelajar Semester Satu Dalam Modul Matematik Kejuruteraan. Diges Politeknik dan Kolej Komuniti Zon Sarawak.

Bagozzi, R.P., & Yi, Y. (1988). On the Evaluation of Structural Equation Models. Journal of the Academy of Marketing Science. 16(1), 74-94.

Barclay, D., Higgins, C., & Thompson, R. (1995). The Partial Least Square Approach to Causal Modeling: Personal Computer Adoption and Use as Illustration. Technology Studies, 2, 284–324.

Branden, K.V., & Hubert, M. 2003. Robustness Properties of a Robust SIMPLS Method. Department of Mathematics, Katholieke Universiteit Leuven, Belgium.

Broussard, S.C. (2002). The Relationship between Classroom Motivation and Academic Achievement in First and Third Graders. (Master thesis). Faculty of the Louisiana State University and Agricultural and Mechanical College, Louisiana State University.

Brownlow. S, & Reasinger, R.D. (2000). Putting off Until Tomorrow What Is Better Done Today: Academic Procrastination as a Function of Motivation toward College Work. Journal of Social Behaviour and Personality, 15(5),15-34.

Carbone.A, Mitchell.I., Gunstone, D. & Hurst.J. (2007). An Exploration of Internal Factors Influencing Studies. Learning of Programming, 15-34.

Chin, W.W. (2010a). How to Write up and Report PLS Analyses. Dlm. V. E.Vinzi, W. W. Chin, J. Henseler & H. Wang (pnyt.). Handbook of Partial Least Squares Concepts, Methods and Applications. Berlin: Springer-Verlag,

Chin, W.W. (2010b). Bootstrap Cross-Validation Indices for PLS Path Model Assessment. Dlm. V. E.Vinzi, W. W. Chin, J. Henseler & H. Wang (eds.). Handbook of Partial Least Squares Concepts, Methods and Applications. Berlin: Springer-Verlag.

Croux, C., & Haesbroeck, G. (2000). Principal Component Analysis Based on Robust Estimators of The Covariance or Correlation Matrix: Influence Functions and Efficiencies. Biometrika,87(3): 603- 618.

Dillon, W.R., & Goldstein, M. (1984). Multivariate Analysis, Methods and Applications. New York: John Wiley & Sons.

Fornell, C., & Larcker, D.F. (1981). Evaluating Structural Equation Models with Unobservable Variables and Measurement Error. Journal of Marketing Research, 48, 39-50.

Hardin, J., &. Rocke, D.M. (2004). Outlier Detection in the Multiple Cluster Setting Using the Minimum Covariance Determinant Estimator. Computational Statistics & Data Analysis. 44(4): 625-638.

Hubert, M., & Branden, K.V. (2003). Robust Methods for Partial Least Squares Regression. Journal of Chemometrics, 17, 537-549.

Hubert, M., Rousseeuw, P.J., & Aelst, S.V. (2004). Robustness. Dlm. Sundt, B. & Teugels, J. (pnyt.). Encyclopedia of Actuarial Sciences. New York: John Wiley.

Hubert, M., Rousseeuw, P.J., & Vanden Branden, K. (2005). ROBPCA: A New Approach to Robust Principal Component Analysis. Technometrics, 47, 64-79.

Jones, J. (2012). The External and Internal Educational Factors that Contribute to Student Achievement and Self-Perceptions of Urban Middle School Title I Students. Rowan University.

Jöreskog, K.G., & Sörbom, D. (2006). Lisrel 8.8: A Guide to the Program and Applications. Illionis: SPSS Inc.

Loehlin, J.C. (2004). Latent Variable Models (Edisi ke-4). New Jersey: Lawrence Erlbaum Associates.

Lohmoller, J.B. (1989). PLS-GUI: A Graphic User Interface for LVPLS (PLS 1.8 PC). Berlin.

Mashithah Khalid (2012). Faktor-faktor Mempengaruhi Motivasi Pembelajaran Terhadap Subjek Ekonomi Mahasiswa Universiti Kebangsaan Malaysia. Fakulti Pendidikan, Universiti Kebangsaan Malaysia.

Mohamad Hasan Omar (2010). Permasalahan yang Mempengaruhi Pembelajaran dan Pencapaian Akademik Pelajar Bumiputera (Tingkatan 4) di Sekolah Menengah Teknik di Johor Bahru. Fakulti Pendidikan, Universiti Teknologi Malaysia.

Mohd Nihra Haruzuan, & Nurul Azilah Ibrahim (2011). Faktor-Faktor yang Mempengaruhi Pencapaian Mata pelajaran Analisis Nyata Pelajar Tahun Akhir SPT dan SPM. Fakulti Pendidikan, Universiti Teknologi Malaysia.

Norawati Hashim (2004). Hubungan Pencapaian Matematik Murid-murid melayu Sekolah Rendah Luar Bandar Mengikut Minat dan Jantina. (Tesis yang tidak diterbitkan). Fakulti Sains dan Teknologi, Universiti Pendidikan Sultan Idris.

Norliza Adnan, Maizah Hura Ahmad, & Robiah Adnan (2006). A Comparative Study on Some Methods for Handling Multicollinearity Problems. MATEMATIKA, 22(2), 109–119.

Nunnally, J.C. (1978). Psychometric Theory (Edisi Ke-2). New York: McGraw-Hill.

O’Brien, R.M. (2007). A Caution Regarding Rules of Thumb for Variance Inflation Factors. Quality & Quantity, 41, 673–690. DOI 10.1007/s11135-006-9018-6

Rousseeuw, P.J., & Van Zomeren, Driessen, K. 1999. A Fast Algorithm for the Minimum Covariance Determinant Estimator. Technometrics, 41, 212-223.

Roziana Aminorlah (2002). Faktor-faktor Halangan Komunikasi dalam Kelas Matematik KBSM: Satu Kajian Tinjauan di Sekolah Menengah di Zon Bangsar, Kuala Lumpur. (Tesis yang tidak diterbitkan). Universiti Utara Malaysia.

Schyns, M., Haesbroeck, G., & Critchley, F. (2009). RelaxMCD: Smooth Optimisation for the Minimum Covariance Determinant Estimator. Computational Statistics and Data Analysis. DOI 10.1016/j.csda.2009.11.005.

Sternberg, R.J., & Hedlund, J. (2002). Practical Intelligence, g and Work Psychology. Human Performance, 15(1/2), 143–160.

Temme, D., Henning, K., & Lutz, H. (2006). PLS Path Modeling– A Software Review. SFB 649 Discussion Paper. Berlin: Institute of Marketing, Humboldt-Universität zu Berlin, Germany.

Tenenhaus, M., Vinzi, V.E., Chatelin, Y.M., & Lauro, C. (2005). PLS Path Modeling. Computational Statistics and Data Analysis, 48(1),159–205.

Vinzi, V.E, Chin, W.W., Henseler, J. & Wang, H. (pnyt.) ( 2008). Handbook of Partial Least Squares: Concepts, Methods and Applications in Marketing and Related Fields. Springer Handbooks ofComputational Statistics. New York: Springer-Verlag.

Vinzi, V.E, Trinchera, L., Squillacciotti, S., & Tenenhaus, M. (2008). REBUS-PLS: A ResponsebasedProcedure for Detecting Unit Segments in PLS Path Modeling. Applied Stochastic Models in Business and Industry, 24(5), 439-458.

Vinzi, V.E, & Russolillo, G. (2013). Partial Least Squares Algorithms and Methods. WIREs Computational Statistics, 5, 1-19

Wetzels, M., Schröder, G.O., & Oppen, C.V. (2009). Using PLS Path Modeling for Assessing Hierarchical Construct Models: Guidelines and Empirical Illustration. MIS Quarterly 33( 1), 177-195.

Wold, H. (1983). Soft Modeling: The Basic Design and Some Extensions. Dlm. K.G. Joreskorg & H. Wold (pnyt.). Systems Under Indirect Observation. Amsterdam: North-Holland.

Zhang, A., & Aasheim, C.L. (2011). Academic Success Factors: An IT Student Perspective. Journal of Information Technology Education, 10, 309-331.

Zulkifley Mohamed, & Kamarulzaman Ibrahim (2009). Pemboleh ubah Pendam Teguh dalam Model Persamaan Berstruktur Kuasa Dua Terkecil Separa. Jurnal Sains dan Matematik, 1 (1), 45-58.

Zulkifli Abd. Hamid, Jamilah Othman, Aminah Ahmad, & Ismi Arif Ismail (2011). Hubungan Antara Penglibatan Ibubapa dan Pencapaian Akademik Pelajar Miskin di Negeri Selangor. Journal of Islamic and Arabic Education, 3(2),31-40.

Downloads

Published

2014-06-11

How to Cite

Mohamed, Z., & Rosli, R. (2014). Development of A Structural Model with Multicollinearity and Outliers Problems: Pembangunan Model Berstruktur Bermasalah Multikolinearan dan Data Pencilan. EDUCATUM Journal of Science, Mathematics and Technology, 1(1), 38–52. Retrieved from https://ojs.upsi.edu.my/index.php/EJSMT/article/view/9