Pemodelan regresi logistik Firth Penalized Maximum Likelihood Estimation pada kepemilikan tempat usaha
Abstract
Pada penelitian sosial sering memperoleh data kategorik dengan proporsi kategori yang diinginkan (sukses) jauh lebih sedikit dibandingkan dengan proporsi kategori yang tidak diinginkan (gagal). Data tersebut dikatakan sebagai separasi sempurna atau rare events. Data dengan rare events bila digunakan dalam regresi termasuk regresi logistik akan menghasilkan estimator parameter yang bias dalam proses Maximum Likelihood Estimation (MLE). Untuk mengatasi kebiasan karena data rare events atau separasi sempurna maka Firth menambahkan unsur penalti matriks informasi Fisher fungsi ln likelihood MLE. Metode tersebut dinamakan Firth Penalized Maximum Likelihood Estimation. Penelitian ini bertujuan untuk memodelkan regresi logistik dengan Firth Penalized Maximum Likelihood Estimation pada data kepemilikan tempat usaha. Model regresi logistik yang diperoleh sudah sesuai dengan data dan menghasilkan bahwa bidang usaha, umur usaha, skala UMKM, dan lokasi usaha berpengaruh terhadap kepemilikan tempat usaha. Dengan demikian, para pelaku UMKM perlu mempertimbangkan dengan bijak kepemilikan tempat usaha.Â
Full Text:
PDFReferences
Agresti, A. (2002). An introduction to categorical data analysis (Second Edi). New Jersey: John Wiley & Sons, Inc Publication.
Antipov, E. (2019). Applying CHAID for logistic regression diagnostics and classification accuracy improvement. (January). https://doi.org/10.2139/ssrn.1412208
Astriyani, R. (2024). Pengaruh lokasi, modal dan kemampuan usaha terhadap keberhasilan usaha. Jurnal Kewirausahaan dan Multi Talenta, 2. https://doi.org/10.38035/jkmt.v2i2
Bourakadi, A., Mentagui, D., and Chakir, B. A. (2022). Hypothesis test of sample mean of random intervals and comparing between methods based on Hausdorff distance and the maximum likelihood ratio. Italian Journal of pure and applied mathematics, 48, 384–398.
BPS. (2021). Kecamatan Ngaliyan dalam Angka 2021. Semarang: Badan Pusat Statistik Kota Semarang.
Cameron, A.C. and Trivedi, P. K. (1998). Regression analysis of count data. Cambridge: Cambridge University Press. https://doi.org/https://doi.org/10.1017/CBO9780511814365
Firth, D. (1993). Bias reduction of maximum likelihood estimates. Biometrika, 80(1), 27–38. https://doi.org/https://doi.org/10.2307/2336755
Holmberg, M. J., and Andersen, L. W. (2020). Estimating risk ratios and risk differences. JAMA, 324(11), 1098. https://doi.org/10.1001/jama.2020.12698
Hosmer, D., and Lemeshow, S. (2000). Applied logistic regression. Canada: A John Wiley & Sons, Inc Publication.
Hutagalung, M. A. I., and Sutarman. (2024). Penalized maximum likelihood estimation dengan algoritma gradient descent pada model regresi logistik multinomial. IJM: Indonesian Journal of Multidisciplinary, 2. Retrieved from https://journal.csspublishing/index.php/ijm
Jain, H., Khunteta, A., and Srivastava, S. (2020). Churn prediction in telecommunication using logistic regression and logit Boost. Procedia Computer Science, 167, 101–112. https://doi.org/10.1016/j.procs.2020.03.187
King, G., Langche Zeng, G. H. E., Alt, J., Freeman, J., Gleditsch, K., Imbens, G., … Zeng, L. (2001). Logistic regression in rare events data. In the Society for Political Methodology. Retrieved from http://GKing.Harvard.Edu.
KlieÅ¡tik, T., KoÄiÅ¡ová, K., and MiÅ¡anková, M. (2015). Logit and probit model used for prediction of financial health of company. Procedia Economics and Finance, 23, 850–855. https://doi.org/10.1016/S2212-5671(15)00485-2
Liu, H., Zhang, Z., Hall, H., Liu, H., and Zhang, &. (2017). Logistic regression with misclassification in binary outcome variables: A method and software. In Behaviormetrika (Vol. 44).
Malau, T., and Joseph, T. (2023). Analisis metode logistik regresi ensemble untuk klasifikasi dengan pra-pemrosesan menggunakan principal component analysis. In IJM: Indonesian Journal of Multidisciplinary (Vol. 1). Retrieved from https://journal.csspublishing/index.php/ijm
Nisa, E. K., and Maslihah, S. (2024). Regresi logistik dan penerapannya. PPSM.
Nisa, E. K., and Miasary, S. D. (2024). Parameter estimation and application of inverse gaussian regression. 020008. https://doi.org/10.1063/5.0194666
Nisa, E. K., and Muanalifah, A. (2021). The comparison results of logit and probit regression on factors of woman criminal. 5(2), 287–293. https://doi.org/10.31764/jtam.v5i2.4150
Putri, S. S., and Budyanra. (2021). Penerapan metode firth’s penalized maximum likelihood estimation pada analisis determinan penyalahgunaan narkoba remaja di Indonesia tahun 2017. Statistika, 21(2), 117–124. https://doi.org/https://doi.org/10.29313/statistika.v21i2.308
Rahman, M. S., and Sultana, M. (2017). Performance of firth-and logF-type penalized methods in risk prediction for small or sparse binary data. BMC Medical Research Methodology, 17(1), 33–48. https://doi.org/10.1186/s12874-017-0313-9
Risnawati, N. (2018). Profil UMK, permasalahan dan upaya pemberdayaannya. Coopetition: Jurnal Ilmiah Manajemen, IX(2).
Sudijono, A. (2015). Pengantar Evaluasi Pendidikan. Jakarta: PT Raja Grafindo Persada.
Suhas, S., Manjunatha, N., Kumar, C. N., Benegal, V., Rao, G. N., Varghese, M., and Gururaj, G. (2023). Firth’s penalized logistic regression: A superior approach for analysis of data from India’s National Mental Health Survey, 2016. Indian Journal of Psychiatry, 65(12), 1208–1213. https://doi.org/10.4103/indianjpsychiatry.indianjpsychiatry_827_23
Tongco, Ma. D. C. (2007). Purposive sampling as a tool for informant selection. Ethnobotany Research & Application, 5(2), 147–158.
Walpole, R. E., Myers, R. H., and Myers, S. L. (2012). Probability & Statistics for Engineers & Scientists. Boston: Pearson Prentice Hall.
Wilks. (1938). The large sample distribution of the likelihood ratio for testing composite hypotheses. American Mathematical Society, 231. Retrieved from https://www.jstor.org/stable/i348755
DOI: https://doi.org/10.26877/aks.v15i3.21088
Refbacks
- There are currently no refbacks.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
AKSIOMA : Jurnal Matematika dan Pendidikan Matematika is licensed under a  Creative Commons Attribution-ShareAlike 4.0 International License.
AKSIOMA : Jurnal Matematika dan Pendidikan Matematika Indexed by:
Â
Copyright of AKSIOMA : Jurnal Matematika dan Pendidikan Matematika
Â
Â