MODIFYING MIXED MODEL NEURAL NETWORKS FOR UNIT-LEVEL PROPORTION SMALL AREA ESTIMATION
Abstract
This paper develops a Small Area Estimation Mixed Model Neural Network (SAE-MNN) for unit-level estimation of area-level proportions under clustered binary responses. The method is motivated by a limitation of conventional generalized linear mixed model (GLMM)-based small area estimation, namely the linear specification of the fixed-effects component on the latent scale, which may be inadequate when auxiliary variables exhibit nonlinear effects and higher-order interactions. The proposed model replaces the linear predictor with a neural-network-based nonlinear function while retaining area-level random effects within a likelihood-based mixed-model framework. Thus, SAE-MNN combines nonlinear function approximation with the borrowing-strength mechanism required for coherent small area inference. The method is evaluated through a controlled simulation study and a real-data application. The simulation study considers four scenarios generated by combining two predictor structures (linear and interaction-based nonlinear) with two levels of between-area heterogeneity (small and large), and compares SAE-MNN with a conventional GLMM and a standard deep neural network (DNN). SAE-MNN performs robustly across all scenarios and is especially effective when nonlinear interaction and substantial area-level heterogeneity coexist. In the most complex scenario, SAE-MNN attains the lowest median RRMSE (8.389%), compared with 11.474% for GLMM and 18.826% for DNN, while maintaining empirical coverage between 0.89 and 0.94. In the real-data application, using KSA segment-level harvest proportions to estimate subdistrict-level monthly harvest proportions, SAE-MNN shows the closest overall agreement with the direct estimator, reproduces the main temporal pattern more faithfully than GLMM, and yields moderate shrinkage without excessive smoothing. Overall, the results indicate that SAE-MNN provides a principled compromise between the rigidity of GLMM and the purely predictive character of DNN, thereby extending hybrid small area estimation methodology to binary and proportional outcomes in data-rich settings with nonlinear auxiliary information and area-level heterogeneity.
Downloads
References
J. D. Merfeld, H. Chen, P. Lahiri, and D. Newhouse, “SMALL AREA ESTIMATION WITH GEOSPATIAL DATA: A PRIMER,” 2024. [Online]. Available: https://unstats.un.org/iswghs/documents/
J. Jiang and P. Lahiri, “MIXED MODEL PREDICTION AND SMALL AREA ESTIMATION,” 2006. doi: https://doi.org/10.1007/BF02595419
E. Berg, “EMPIRICAL BEST PREDICTION OF SMALL AREA MEANS BASED ON A UNIT-LEVEL GAMMA-POISSON MODEL,” J. Surv. Stat. Methodol., vol. 11, no. 4, pp. 873–894, Sep. 2023. doi: https://doi.org/10.1093/jssam/smac026
N. Tzavidis, L.-C. Zhang, A. Luna, T. Schmid, and N. Rojas-Perilla, “FROM START TO FINISH: A FRAMEWORK FOR THE PRODUCTION OF SMALL AREA OFFICIAL STATISTICS,” 2018. [Online]. Available: https://academic.oup.com/jrsssa/article/181/4/927/7072057. doi: https://doi.org/10.1111/rssa.12364
D. Morales, M. D. Esteben, A. Perez, and T. Hobza, “A COURSE ON SMALL AREA ESTIMATION AND MIXED MODEL,” 2021. doi: https://doi.org/10.1007/978-3-030-63757-6
O. Faltys, T. Hobza, and D. Morales, “SMALL AREA ESTIMATION UNDER AREA-LEVEL GENERALIZED LINEAR MIXED MODELS,” Commun. Stat. Simul. Comput., vol. 51, no. 12, pp. 7404–7426, 2022. doi: https://doi.org/10.1080/03610918.2020.1836216
P. J. Farrell, B. Macgibbon, and T. J. Tomberlin, “EMPIRICAL BAYES ESTIMATORS OF SMALL AREA PROPORTIONS IN MULTISTAGE DESIGNS,” 1997.
J. Jiang and P. Lahiri, “EMPIRICAL BEST PREDICTION FOR SMALL AREA INFERENCE WITH BINARY DATA,” Ann. Inst. Stat. Math., vol. 53, pp. 217–243, 2001. doi: https://doi.org/10.1023/A:1012410420337
T. Hobza and D. Morales, “EMPIRICAL BEST PREDICTION UNDER UNIT-LEVEL LOGIT MIXED MODELS,” J. Off. Stat., vol. 32, no. 3, pp. 661–692, Sep. 2016. doi: https://doi.org/10.1515/jos-2016-0034
S. Sugasawa and T. Kubokawa, “TRANSFORMING RESPONSE VALUES IN SMALL AREA PREDICTION,” Comput. Stat. Data Anal., vol. 114, pp. 47–60, Oct. 2017. doi: https://doi.org/10.1016/j.csda.2017.03.017
P. Corral, I. Molina, A. Cojocaru, and S. Segovia, “GUIDELINES TO SMALL AREA ESTIMATION FOR POVERTY MAPPING,” 2022. doi: https://doi.org/10.1596/37728
A. Kurnia, D. Surida, S. Muchlisoh, I. Wulandari, and D. Handayani, “SMALL AREA ESTIMATION UNDER A PSEUDO-UNIT LEVEL MODEL WITH FIRST-ORDER AUTOREGRESSIVE TIME EFFECTS AND MEASUREMENT ERROR,” IAENG International Journal of Applied Mathematics, vol. 54, no. 3, pp. 365–372, 2024.
N. Tzavidis, N. Salvati, M. Pratesi, and R. Chambers, “M-QUANTILE MODELS WITH APPLICATION TO POVERTY MAPPING,” Stat. Methods Appt., vol. 17, no. 3, pp. 393–411, 2008. doi: https://doi.org/10.1007/s10260-007-0070-8
H. Li, Y. Liu, and R. Zhang, “SMALL AREA ESTIMATION UNDER TRANSFORMED NESTED-ERROR REGRESSION MODELS,” Statistical Papers, vol. 60, no. 4, pp. 1397–1418, Aug. 2019. doi: https://doi.org/10.1007/s00362-017-0879-7
Y. Kurniawati, H. Wijayanto, A. Kurnia, D. D. Domiri, and B. Susetyo, “SELECTION OF MULTINOMIAL LOGIT MODELS BASED ON ACCURACY RECLASSIFICATION OF THE AREA SAMPLING FRAME LABELS,” Science & Technology Asia |, vol. 28, no. 2, 2023.
J. Jiang and J. S. Rao, “ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION ROBUST SMALL AREA ESTIMATION: AN OVERVIEW,” 2020. doi: https://doi.org/10.1146/annurev-statistics-031219-041212
D. Newhouse, J. D. Merfeld, A. Pudugramam, R. T. Swartz, and P. Lahiri, “SMALL AREA ESTIMATION OF MONETARY POVERTY IN MEXICO USING SATELLITE IMAGERY AND MACHINE LEARNING,” 2022. [Online]. Available: http://www.worldbank.org/prwp. doi: https://doi.org/10.1596/1813-9450-10175
P. Bilton, G. Jones, S. Ganesh, and S. Haslett, “CLASSIFICATION TREES FOR POVERTY MAPPING,” Comput. Stat. Data Anal., vol. 115, pp. 53–66, Nov. 2017. doi: https://doi.org/10.1016/j.csda.2017.05.009
M. Viljanen, L. Meijerink, L. Zwakhals, and J. van de Kassteele, “A MACHINE LEARNING APPROACH TO SMALL AREA ESTIMATION: PREDICTING THE HEALTH, HOUSING AND WELL-BEING OF THE POPULATION OF NETHERLANDS,” Int. J. Health Geogr., vol. 21, no. 1, Dec. 2022. doi: https://doi.org/10.1186/s12942-022-00304-5
P. Krennmair and T. Schmid, “FLEXIBLE DOMAIN PREDICTION USING MIXED EFFECTS RANDOM FORESTS,” J. R. Stat. Soc. Ser. C Appl. Stat., vol. 71, no. 5, pp. 1865–1894, Nov. 2022. doi: https://doi.org/10.1111/rssc.12600
P. Krennmair, W. ¨ Nora, and T. Schmid, “TREE-BASED MACHINE LEARNING IN SMALL AREA ESTIMATION,” 2022.
A. Hajjem, F. Bellavance, and D. Larocque, “MIXED-EFFECTS RANDOM FOREST FOR CLUSTERED DATA,” J. Stat. Comput. Simul., vol. 84, no. 6, pp. 1313–1328, Jun. 2014. doi: https://doi.org/10.1080/00949655.2012.741599
R. Ananda, K. A. Notodiputro, and M. N. Aidi, “MODIFIED MIXED EFFECTS RANDOM FOREST IN SMALL AREA ESTIMATION USING PCA AND ROTATION FOREST WITH CORRELATED AUXILIARY VARIABLES,” Scientific Journal of Informatics, vol. 11, no. 3, pp. 705–720, Aug. 2024. doi: https://doi.org/10.15294/sji.v11i3.10633
N. Frink and T. Schmid, “SMALL AREA ESTIMATION WITH GENERALIZED RANDOM FORESTS: ESTIMATING POVERTY RATES IN MEXICO,” Jun. 2024, [Online]. Available: http://arxiv.org/abs/2406.03861
D. W. Triscowati, B. Sartono, A. Kurnia, D. Dirgahayu, and A. W. Wijayanto, “CLASSIFICATION OF RICE-PLANT GROWTH PHASE USING SUPERVISED RANDOM FOREST METHOD BASED ON LANDSAT-8 MULTITEMPORAL DATA,” International Journal of Remote Sensing and Earth Sciences (IJReSES), vol. 16, no. 2, p. 187, Apr. 2020. doi: https://doi.org/10.30536/j.ijreses.2019.v16.a3217
D. W. Triscowati, B. Sartono, A. Kurnia, D. D. Domiri, and A. W. Wijayanto, “MULTITEMPORAL REMOTE SENSING DATA FOR CLASSIFICATION OF FOOD CROPS PLANT PHASE USING SUPERVISED RANDOM FOREST,” in Sixth Geoinformation Science Symposium, S. B. Wibowo, A. B. Rimba, A. A. Aziz, S. Phinn, J. T. Sri Sumantyo, H. Widyasamratri, and S. Arjasakusuma, Eds., SPIE, Nov. 2019, p. 10. doi: https://doi.org/10.1117/12.2547216
K. Kita et al., “BIMODAL ARTIFICIAL INTELLIGENCE USING TABNET FOR DIFFERENTIATING SPINAL CORD TUMORS—INTEGRATION OF PATIENT BACKGROUND INFORMATION AND IMAGES,” iScience, vol. 26, no. 10, Oct. 2023. doi: https://doi.org/10.1016/j.isci.2023.107900
Y. Xiong, H. J. Kim, and V. Singh, “MIXED EFFECTS NEURAL NETWORKS (MENETS) WITH APPLICATIONS TO GAZE ESTIMATION,” 2019. doi: https://doi.org/10.1109/CVPR.2019.00793
G. Simchoni and S. Rosset, “INTEGRATING RANDOM EFFECTS IN DEEP NEURAL NETWORKS,” Jun. 2023, [Online]. Available: http://arxiv.org/abs/2206.03314
M. N. Tran, N. Nguyen, D. Nott, and R. Kohn, “BAYESIAN DEEP NET GLM AND GLMM,” Journal of Computational and Graphical Statistics, vol. 29, no. 1, pp. 97–113, Jan. 2019. doi: https://doi.org/10.1080/10618600.2019.1637747
B. Yang et al., “BRAN2SAT: REDUNDANT SATISFIABILITY LOGIC IN LYAPUNOV-BASED DISCRETE HOPFIELD NEURAL NETWORK,” J. Comput. Des. Eng., vol. 12, no. 4, pp. 185–204, Apr. 2025. doi: https://doi.org/10.1093/jcde/qwaf039
Y. Chang, M. S. Mohd Kasihmuddin, W. N. Aqlili Ruzai, Y. Guo, and J. Chen, “WEIGHTED C-TYPE RANDOM 2 SATISFIABILITY IN DISCRETE HOPFIELD NEURAL NETWORK,” Eng. Appl. Artif. Intell., vol. 160, p. 111760, 2025. doi: https://doi.org/10.1016/j.engappai.2025.111760
Copyright (c) 2026 Ade Riyawan, Muhammad Nur Aidi, Budi Susetyo, Anang Kurnia
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:
- 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.
- 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).
- 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.
1.gif)
