Application of Propensity Score Matching for Analyzing Factors Contributing to Pre-Diabetes

Oktaviani Aisyah Putri, Anwar Fitrianto, Aam Alamudi

Abstract


Inappropriate comparisons between control and treatment groups can be caused by overlapping factors, usually called confounders. Propensity score methods help reduce bias from measured confounding by summarizing the distribution of multiple measured confounders into a single score, based on the probability of receiving treatment. This study applies binary logistic regression to estimate propensity scores and identify risk factors that significantly influence complications in fasting blood glucose levels. Nearest Neighbor Matching (NNM) is used with various caliper and score orders to determine the most effective combination in reducing bias. The results show that gender becomes a confounding variable. Both the order of propensity scores and caliper selection affect the outcome of the matching process. Matching with a random order and caliper yields the best result, with 99,93 percent reduction bias. The significance of the average treatment effect for treated (ATT), all condition order with caliper indicates that gender have a positive relationship and significantly affects fasting blood glucose levels. Also, based on the matching results with the best combination, it indicates that age, academic position, structural position, education level, and lecturer performance do not influence abnormal fasting blood sugar (FBS).


Keywords


binary logistic regression; caliper; fasting blood glucose levels; propensity score matching (PSM); structural positions

Full Text:

PDF

References


[1] J. Kahlert, S. B. Gribsholt, H. Gammelager, O. M. Dekkers and G. Luta, "Control of confounding in the analysis phase–an overview for clinicians," Clinical epidemiology, vol. 9, pp. 195-204, 2017.
[2] N. Faulina, K. Nisa, D. Aziz and E. Setiawan, "Analisis propensity score matching pada kejadian diabetes melitus yang memuat faktor confounding," Jurnal Siger Matematika, vol. 2, no. 2, pp. 43-51, 2021.
[3] M. Webster-Clark, T. Sturmer, T. Wang, K. Man, D. Marinac-Dabic, K. J. Rothman, A. R. Ellis, M. Gokhale, M. Lunt, C. Girman and R. Glynn, "Using propensity scores to estimate effects of treatment initiation decisions: state of the science," Statistics in medicine, vol. 40, no. 7, pp. 1718-1735, 2021.
[4] F. Cottone, A. Anota, B. Frack, G. S. Collins and F. Efficace, "Propensity score methods and regression adjustment for analysis of nonrandomized studies with health‐related quality of life outcomes," Pharmacoepidemiology and Drug Safety, vol. 28, no. 5, pp. 690-699, 2019.
[5] P. C. Austin, "An introduction to propensity score methods for reducing the effects of confounding in observational studies," Multivariate Behav Res, vol. 46, no. 3, pp. 399-424, 2011.
[6] P. C. Austin, "A comparison of 12 algorithms for matching on the propensity score," Statist. Med, vol. 33, pp. 1057-1069, 2014.
[7] Y. Wang, H. Cai, C. Li, Z. Jiang, L. Wang, J. Song and J. Xia, "Optimal caliper width for propensity score matching of three treatment groups: a Monte Carlo study," PloS one, vol. 8, no. 12, pp. 1-7, 2013.
[8] S. T. Simanjuntak and C. T. Wahyanti, "Analisis kinerja dosen melaksanakan Tri Dharma Perguruan Tinggi pada masa pandemi covid-19: studi kasus di Universitas Kristen Satya Wacana," Jurnal Ilmia, Manajemen Sumber Daya Manusia, vol. 5, no. 1, pp. 86-101, 2021.
[9] W. Kusgiyanto, S. Suroto and E. Ekawati, "Analisis hubungan beban kerja fisik, masa kerja, usia, dan jenis kelamin terhadap tingkat kelelahan kerja pada pekerja bagian pembuatan kulit lumpia di Kelurahan Kranggan Kecamatan Semarang Tengah," Jurnal Kesehatan Masyarakat, vol. 5, no. 5, pp. 413-423, 2017.
[10] O. Mungkasa, "Bekerja dari rumah (working from home/wfh): menuju tatanan baru era pandemi COVID-19," Jurnal Perencanaan Pembangunan: The Indonesian, vol. 4, no. 2, pp. 126-150, 2020.
[11] I. A. Wati, K. A. Sari and D. Lubis, "Perilaku deteksi dini penyakit tidak menular pada dosen di Fakultas Kedokteran Universitas Udayana," Arc. Com. Health, vol. 4, no. 1, pp. 86-96, 2017.
[12] A. Rudi and H. N. Kwureh, "Faktor risiko yang mempengaruhi kadar gula darah puasa pada pengguna layanan laboratorium," Wawasan Kesehatan, vol. 3, no. 2, pp. 33-39, 2017.
[13] A. Agresti, Categorical Data Analysis, New York: John Willey and Son.Inc., 2013.
[14] J. F. Hair, W. C. Black, B. J. Babi and R. E. Anderson, Multivariate Data Analysis 7th Edition, England: Pearson Education Limited, 2014.
[15] D. W. Hosmer and Lemeshow, Applied Logistic Regression, New York: John Willey and Sons, 2000.
[16] Q. Li, J. S. Racine and J. M. Wooldridge, "Estimating average treatment effects with continuous and discrete covariates: The case of Swan-Ganz catheterization," American Economic Review, vol. 98, no. 2, p. 357−362, 2008.
[17] S. Hasanah and B. W. Otok, "Perbandingan metode propensity score matching-support vector machine dan propensity score matching-regresi logistik biner pada kasus HIV/AIDS," Sainmatika: Jurnal Ilmiah Matematika dan Ilmu Pengetahuan Alam, vol. 18, no. 1, p. 93−107, 2021.
[18] N. Ariani, R. Alfian and E. Prihandiwati, "Tingkat perilaku pengobatan, kepatuhan minum obat, dan kadar gula darah pasien diabetes mellitus rawat jalan di RSUD Brigjend. H. Hasan Basry Kandangan," Jurnal Ilmiah Manuntung, vol. 8, no. 1, pp. 156-162, 2022.




DOI: https://doi.org/10.18860/cauchy.v10i2.32754

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Anwar Fitrianto

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

Editorial Office
Mathematics Department,
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
Faximile (+62) 341 558933
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.