MIXED-EFFECT MODELS WITH RESTRICTED MAXIMUM LIKELIHOOD (REML), BOOT-STRAPPED REML AND BAYESIAN INFERENCE IN APPLICATION OF GAPMINDER DATA

  • Asysta Amalia Pasaribu Department of Statistics, School of Computer Science, Bina Nusantara University, Indonesia https://orcid.org/0000-0003-0753-5772
  • Kusman Sadik Study Program of Statistics and Data Science, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0000-0001-8361-8057
  • Anang Kurnia Study Program of Statistics and Data Science, School of Data Science, Mathematics, and Informatics, IPB University, Indonesia https://orcid.org/0000-0001-9409-2361
DOI: https://doi.org/10.30598/barekengvol20iss3pp1985-1998
Keywords: Bayesian MCMC, Bayesian theorem, Boot-Strapped REML, Gapminder data, REML

Abstract

Mixed effects model combines fixed effects and random effects, allowing for the analysis of data with both fixed and random variations. This modeling approach is widely utilized across various fields. In R, the lme4 package is commonly employed to estimate mixed effects models using Restricted Maximum Likelihood (REML). There are several methods for estimating model parameters, including Bayesian inference, which has gained prominence with ongoing research advancements. Bayesian inference using Markov Chain Monte Carlo (MCMC) is among the most widely used Bayesian methods. Bayesian inference leverages probabilistic distributions to estimate parameters.to understand the general overview of life expectancy, serving as an indicator of survival time across different continents in the Gapminder dataset, it's essential to identify relevant variables after computing mixed effects predictions using Maximum Likelihood and REML estimation. This involves predicting life expectancy by integrating both random and fixed effects, determining relevant variables after estimating the Mixed Effects Model using REML Bootstrap estimation, and identifying influential variables after estimating the Mixed Effects Model using Bayesian MCMC inference. The methods employed include REML, Bootstrapped-REML, and Bayesian MCMC. The results indicate that all inference methods can be utilized to estimate parameters, with all predictor variables influencing life expectancy, except for the population variable. Further research is recommended to utilize data with more complex predictor variables.

Downloads

Download data is not yet available.

References

S. W. Raudenbush, HLM 6: HIERARCHICAL LINEAR AND NONLINEAR MODELING. SCIENTIFIC SOFTWARE INTERNATIONAL, 2004.

K. Lee, “ASSOCIATIONS BETWEEN CUMULATIVE POVERTY AND CHILDREN’S ACADEMIC OUTCOMES: ABSOLUTE VERSUS RELATIVE POVERTY,” The British Journal of Social Work, p. bcaf001, 2025.doi : https://doi.org/10.1093/bjsw/bcaf001

A. M. Eyasu, T. Zewotir, and Z. G. Dessie, “IMPACT OF CROP COMMERCIALIZATION ON MULTIDIMENSIONAL POVERTY IN RURAL ETHIOPIA: PROPENSITY SCORE APPROACH,” Frontiers in Public Health, vol. 12, p. 1412670, 2025.doi : https://doi.org/10.3389/fpubh.2024.1412670

N. Diz-Rosales, M. J. Lombardía, and D. Morales, “POVERTY MAPPING UNDER AREA-LEVEL RANDOM REGRESSION COEFFICIENT POISSON MODELS,” Journal of Survey Statistics and Methodology, vol. 12, no. 2, pp. 404–434, 2024. doi : https://doi.org/10.1093/jssam/smad036

A. E. N. Mouteyica and N. Ngepah, “EXPLORING HEALTH OUTCOME DISPARITIES IN AFRICAN REGIONAL ECONOMICS COMMUNITIES: A MULTILEVEL LINEAR MIXED-EFFECT ANALYSIS,” BMC Public Health, vol. 25, no. 1, p. 175, 2025.doi : https://doi.org/10.1186/s12889-025-21306-5

Q. Liu et al., “DEVELOPMENT AND VALIDATION OF PREDICTION MODELS FOR INCIDENT REVERSIBLE COGNITIVE FRAILTY BASED ON SOCIAL-ECOLOGICAL PREDICTORS USING GENERALIZED LINEAR MIXED MODEL AND MACHINE LEARNING ALGORITHMS: A PROSPECTIVE COHORT STUDY,” Journal of Applied Gerontology, vol. 44, no. 2, pp. 255–266, 2025.doi : https://doi.org/10.1177/07334648241270052

M. Scandola and E. Tidoni, “RELIABILITY AND FEASIBILITY OF LINEAR MIXED MODELS IN FULLY CROSSED EXPERIMENTAL DESIGNS,” Advances in Methods and Practices in Psychological Science, vol. 7, no. 1, p. 25152459231214454, 2024.doi : https://doi.org/10.1177/25152459231214454

S. Smout, K. Champion, S. O’Dean, M. Teesson, L. Gardner, and N. Newton, “ANXIETY, DEPRESSION AND DISTRESS OUTCOMES FROM THE HEALTH4LIFE INTERVENTION FOR ADOLESCENT MENTAL HEALTH: A CLUSTER-RANDOMIZED CONTROLLED TRIAL,” Nature Mental Health, vol. 2, no. 7, pp. 818–827, 2024.doi : https://doi.org/10.1038/s44220-024-00246-w

J. Kanyama Busanga and P. Njuho, “LINEAR MIXED MODEL EFFECTS IN META ANALYSIS OF AGRICULTURAL DATA.,” International Journal of Agricultural & Statistical Sciences, vol. 20, no. 2, 2024.doi : https://doi.org/10.59467/IJASS.2024.20.511

J. Caviedes, J. T. Ibarra, L. Calvet-Mir, S. Álvarez-Fernández, and A. B. Junqueira, “INDIGENOUS AND LOCAL KNOWLEDGE ON SOCIAL-ECOLOGICAL CHANGES IS POSITIVELY ASSOCIATED WITH LIVELIHOOD RESILIENCE IN A GLOBALLY IMPORTANT AGRICULTURAL HERITAGE SYSTEM,” Agricultural Systems, vol. 216, p. 103885, 2024. doi : https://doi.org/10.1016/j.agsy.2024.103885

J. C. Coltherd et al., “HEALTHY CATS TOLERATE LONG-TERM DAILY FEEDING OF CANNABIDIOL,” Frontiers in veterinary science, vol. 10, p. 1324622, 2024.doi : https://doi.org/10.3389/fvets.2023.1324622

F. Massa, M. Scavino, and G. Muniz-Terrera, “A BAYESIAN NON-LINEAR MIXED-EFFECTS MODEL FOR ACCURATE DETECTION OF THE ONSET OF COGNITIVE DECLINE IN LONGITUDINAL AGING STUDIES,” arXiv preprint arXiv:2502.08418, 2025.doi : https://doi.org/10.3390/stats8030074

K. Zhong, F. L. Schumacher, L. M. Castro, and V. H. Lachos, “BAYESIAN ANALYSIS OF CENSORED LINEAR MIXED‐EFFECTS MODELS FOR HEAVY‐TAILED IRREGULARLY OBSERVED REPEATED MEASURES,” Statistics in Medicine, vol. 44, no. 3–4, p. e10295, 2025.doi : https://doi.org/10.1002/sim.10295

P.-F. Wang, L.-H. Dong, L.-F. Xie, and Z. Miao, “CONSTRUCTION OF BIOMASS MODELS FOR LARIX OLGENSIS PLANTATION USING HIERARCHICAL BAYESIAN SEEMINGLY UNRELA-TED REGRESSION,” Ying yong sheng tai xue bao= The journal of applied ecology, vol. 36, no. 5, pp. 1298–1308, 2025.

E. Smenderovac et al., “MIXED MODEL APPROACHES CAN LEVERAGE DATABASE INFORMATION TO IMPROVE THE ESTIMATION OF SIZE-ADJUSTED CONTAMINANT CONCENTRATIONS IN FISH POPULATIONS,” Environmental Science & Technology, vol. 59, no. 10, pp. 4797–4806, 2025.doi : https://doi.org/10.1021/acs.est.4c10303

N. Laird, N. Lange, and D. Stram, “MAXIMUM LIKELIHOOD COMPUTATIONS WITH REPEATED MEASURES: APPLICATION OF THE EM ALGORITHM,” Journal of the American Statistical Association, vol. 82, no. 397, pp. 97–105, 1987.doi : https://doi.org/10.1080/01621459.1987.10478395

R. I. Jennrich and M. D. Schluchter, “UNBALANCED REPEATED-MEASURES MODELS WITH STRUCTURED COVARIANCE MATRICES,” Biometrics, pp. 805–820, 1986. doi : https://doi.org/10.2307/2530695

T. Asparouhov, “GENERAL MULTI-LEVEL MODELING WITH SAMPLING WEIGHTS,” Communications in Statistics—Theory and Methods, vol. 35, no. 3, pp. 439–460, 2006. doi : https://doi.org/10.1080/03610920500476598

G. Molenberghs and G. Verbeke, Models for discrete longitudinal data, vol. 22. Springer, 2005.

A. Veiga, P. W. Smith, and J. J. Brown, “THE USE OF SAMPLE WEIGHTS IN MULTIVARIATE MULTILEVEL MODELS WITH AN APPLICATION TO INCOME DATA COLLECTED BY USING A ROTATING PANEL SURVEY,” Journal of the Royal Statistical Society Series C: Applied Statistics, vol. 63, no. 1, pp. 65–84, 2014.doi : https://doi.org/10.1111/rssc.12020

R. Steele, “MODEL SELECTION FOR MULTILEVEL MODELS,” The SAGE handbook of multilevel modeling, pp. 109–125, 2013.doi : https://doi.org/10.4135/9781446247600.n7

K.-R. Koch and K.-R. Koch, “BAYES’ THEOREM,” Bayesian Inference with Geodetic Applications, pp. 4–8, 1990.doi : https://doi.org/10.1007/BFb0048702

B. Efron, “BAYES’ theorem in the 21st century,” Science, vol. 340, no. 6137, pp. 1177–1178, 2013.doi : https://doi.org/10.1126/science.1236536

A. Ebert, K. Mengersen, F. Ruggeri, and P. Wu, “CURVE REGISTRATION OF FUNCTIONAL DATA FOR APPROXIMATE BAYESIAN COMPUTATION,” Stats, vol. 4, no. 3, pp. 762–775, 2021.doi : https://doi.org/10.3390/stats4030045

S. S. Qian, C. A. Stow, and M. E. Borsuk, “ON MONTE CARLO METHODS FOR BAYESIAN INFERENCE,” Ecological modelling, vol. 159, no. 2–3, pp. 269–277, 2003.doi : https://doi.org/10.1016/S0304-3800(02)00299-5

C. M. Crainiceanu and D. Ruppert, “LIKELIHOOD RATIO TESTS IN LINEAR MIXED MODELS WITH ONE VARIANCE COMPONENT,” Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 66, no. 1, pp. 165–185, 2004.doi : https://doi.org/10.1111/j.1467-9868.2004.00438.x

Published
2026-04-08
How to Cite
[1]
A. A. Pasaribu, K. Sadik, and A. Kurnia, “MIXED-EFFECT MODELS WITH RESTRICTED MAXIMUM LIKELIHOOD (REML), BOOT-STRAPPED REML AND BAYESIAN INFERENCE IN APPLICATION OF GAPMINDER DATA”, BAREKENG: J. Math. & App., vol. 20, no. 3, pp. 1985-1998, Apr. 2026.
Issue
Vol 20 No 3 (2026): BAREKENG: Journal of Mathematics and Its Application
Section
Articles

Copyright (c) 2026 Asysta Amalia Pasaribu, Kusman Sadik, Anang Kurnia

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this Journal agree to the following terms:

  1. Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
  2. Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
  3. Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.