Comparison of the Performance of Restricted Maximum Likelihood and MINQUE Methods for Multilevel Data on High School Education Quality in West Java

Fitri Aulia; Budi Susetyo; Kusman Sadik

doi:10.32628/IJSRSET

Authors

Fitri Aulia Department of Statistics, IPB University, Bogor, Indonesia Author
Budi Susetyo Department of Statistics, IPB University, Bogor, Indonesia Author
Kusman Sadik Department of Statistics, IPB University, Bogor, Indonesia Author

DOI:

https://doi.org/10.32628/IJSRSET

Keywords:

Jacknife, Multilevel regression, MINQUE, REML

Abstract

The development of research in various disciplines often results in tiered or hierarchical data structures. In analyzing the quality of education at the high school level in West Java, multilevel data often needs to be processed to account for the hierarchical structure of educational data. Two popular methods for estimating parameters in such models are the Restricted Maximum Likelihood (REML) and Minimum Norm Quadratic Unbiased Estimation (MINQUE) methods. This study aims to compare the performance of these two methods in handling multilevel data concerning high school education quality in West Java. The results of this study found that there is not much difference in parameter values between the REML and Jackknife MINQUE estimates. Regarding significance at the 5% significance level, the Jackknife MINQUE estimate yields a smaller p-value compared to the REML estimate. Based on empirical results from the multilevel model on high school education quality data in West Java, the best-recommended model is the Jackknife MINQUE model.

Downloads

Download data is not yet available.

References

Ali S, Shah SA, Zubair S, Hussain S. (2021). A comparative study of estimators in multilevel linear models. PLoS ONE, 16(11) e0259960. https://doi.org/10.1371/journal. pone.0259960

Astutik, Yayuk Setyaning. (2014). Maximum Likelihood Estimations (MLE) Untuk Regresi Multilevel. Tesis, Universitas Internasional Batam.

Box, George E.P., dan George C. Tiao. (1992). Bayesian Inference in Statistical Analysis Bayesian Inference in Statistical Analysis.

Carpenter J, Goldstein H, Rashbash J. A Non-Paramteric Bootsrap for Multilevel Model. Multilevel Modelling Newsletter.

Delpish AN. Comparison of Estimators in Hierarichal Linear Modelling: Restricted Maximum Likelihood versus Bootsrap via Minimum Norm Quadratic Unbiased Estimators.

Draper, N.R. dan Smith, H. (1992). Applied Regression Analysis, Second Edition. John Wiley and sons, Inc. New York.

Efron, B. dan R. J. Tibshirani. (1993). An Introduction to The Bootstrap. Chapman and Hall, New York.

Falk, C.F., Vogel, T.A., Hammami, S. et al. (2023). Multilevel mediation analysis in R: A Comparion bootsrap and Bayesian approaches. Behav Res.

Goldstein, H. (1995). Mulitilevel Statistical Models Second Edition. Halsted. New York.

Goldstein, H. (2011). Multilevel Statistical Models: 4th Edition. Wiley Series In Probability And Statistics. John Wiley & Sons, Ltd: UK.

Hox, J. J. (2010). Multilevel Analysis: Techniques and Applications Second Edition. Great Britain: Routledge.

Ilagan, M.J., Caron,P.O., Miocevic Milica. (2023). Multilevel analysis of matching behavior: A comparison of maximum likelihood and bayesian estimation. Montreal, QC, Canada.

Jones, B. S. dan Steenbergen, M. R. (2002). Modeling Multilevel Data Structure. American Journal of Political Science. 46: 218-237.

Myers, R.H. (1990) Classical and modern regression with applications. PWS-Kent Publishing, Boston.

Nau Dewa YY, Prasetyo A. (2022). Faktor-Faktor yang Memengaruhi Partisipasi Sekolah Penduduk Usia 16-18 Tahun (SMA Sederajat) Di Provinsi Jawa Barat pada Tahun 2020. Semin. Nas. Off. Stat. 2022(1), 175–184. doi:10.34123/semnasoffstat.v2022i1.1250.

Ntzoufras, I. (2009). Bayesian Modelling Using WinBUGS. United States: John Wiley and Sons.

Raudenbush, S. W. (2002). Hierarchical Linear Models: Application and Data Analysis Methods, 2nd edition. Sage: Thousand Oaks.

Rao CR. (19700 Estimation of Heteroscedastic Variances in Linear Models. Journal of the American Statistical Association. 65(329):161-72.

Rao CR. (1971a). Estimation of variance and covariance components-MINQUE theory. J. Multivar. Anal. 1(3):257–275. doi:10.1016/0047-259X(71)90001-7.

Rao CR. (1971b). Estimation of Variance and Covariance Theory. :257–275.

Snidjers TA, Boskers RJ. Multilevel analysis: An Introduction to Basic and Advanced Multilevel Modelling

Suncaka, Eko. (2023). Meninjau Permasalahan Rendahnya Kualitas Pendidikan di Indonesia. UNISAN Jurnal.

Susetyo B, Fitrianto A. (2022). Evaluation of Accreditation and National Examination using Multilevel Generalized Structured Component Analysis. J. Pendidik. Progresif. 12(1):294–306. doi:10.23960/jpp.v12.i1.202223.

Swallow WH, Monahan JF. (1984). Monte Carlo Compaison of ANOVA, MIVQUE, REML, and ML Estimators of Variance Components. Techno Metrics

Wasserman, S., dan Bockenholt, U. (1989). Bootstrapping: Applications to psychophysiology. Psychophysiology. 26(2): 208–221. https://doi.org/10.1111/j.1469-8986.1989.tb03159.x

West, B. T., Welch, K. B. dan Galecki, A. T. (2015). Linier Mixed Models: A Practical Guide Using Statistical Software: Second Edtion. CRC Press: New York