Kernel-Truncated Spline: Estimator Fleksibel untuk Regresi Nonparametrik

Rahmat Hidayat; Isma Muthahharah; Resmawan Resmawan

doi:10.37905/euler.v13i2.33062

Kernel-Truncated Spline: Estimator Fleksibel untuk Regresi Nonparametrik

Rahmat Hidayat, Isma Muthahharah, Resmawan Resmawan

Abstract

This study aims to develop a multivariable nonparametric regression model using a hybrid approach that combines Spline and kernel estimators. This method is proposed to address the limitations of conventional nonparametric models that typically apply a single type of estimator across all predictor variables, regardless of their individual patterns. In this approach, predictors with oscillatory patterns are modeled using truncated Spline regression, while variables exhibiting complex nonlinear behavior are modeled using a Gaussian kernel estimator. The combined model is constructed and estimated using the Ordinary Least Square (OLS) method and applied to data on the average years of schooling in South Sulawesi Province, Indonesia. Results indicate that the model using two Spline knots and an optimal bandwidth for the kernel component yields the lowest Generalized Cross Validation (GCV) value of 0.142, outperforming models with one or three knots. The best-fitting model achieves a coefficient of determination (R²) of 91.214% and a Mean Squared Error (MSE) of 0.0461. These findings suggest that the hybrid regression approach offers greater flexibility and accuracy in modeling multivariable social data.

Keywords

Nonparametric; Spline; Kernel; GCV; Regression

Full Text:

PDF

References

C. Hazlett, “Kernel Balancing: A Flexible Non-Parametric Weighting Procedure for Estimating Causal Effects,” Stat. Sin., vol. 30, no. 3, pp. 1155–1189, 2020.

S. Węglarczyk, “Kernel density estimation and its application,” ITM Web Conf., vol. 23, p. 00037, 2018, doi: 10.1051/itmconf/20182300037.

A. Perperoglou, W. Sauerbrei, M. Abrahamowicz, and M. Schmid, “A review of spline function procedures in R,” BMC Med. Res. Methodol., vol. 19, no. 1, p. 46, 2019, doi: 10.1186/s12874-019-0666-3.

J. Gauthier, Q. V. Wu, and T. A. Gooley, “Cubic splines to model relationships between continuous variables and outcomes: a guide for clinicians,” Bone Marrow Transplant., vol. 55, pp. 675–680, 2020, doi: 10.1038/s41409-019-0679-x.

J. P. Cohen, C. C. Coughlin, and J. M. Clapp, “Local Polynomial Regressions versus OLS for Generating Location Value Estimates,” The Journal of Real Estate Finance and Economics, No. 2015-14, doi: 10.20955/wp.2015.014.

T. Guo et al., “A Review of Wavelet Analysis and Its Applications: Challenges and Opportunities,” IEEE Access, vol. 10, pp. 58869–58903, 2022, doi: 10.1109/ACCESS.2022.3179517.

W. Yao, Y. Weng, and J. M. Catchmark, “Improved cellulose X-ray diffraction analysis using Fourier series modeling,” Cellulose, vol. 27, no. 10, pp. 5563–5579, 2020, doi: 10.1007/s10570-020-03177-8.

C. Lee, D. Koo, and D. W. Zingg, “Comparison of B-Spline Surface and Free-Form Deformation Geometry Control for Aerodynamic Optimization,” AIAA J., vol. 55, no. 1, pp. 228–240, 2017, doi: 10.2514/1.J055102.

M. Eisen and A. Ribeiro, “Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks,” IEEE Trans. Signal Process., vol. 68, pp. 2977–2991, 2020, doi: 10.1109/TSP.2020.2988255.

H. Jiang et al., “Mobile Internet Quality Estimation using Self-Tuning Kernel Regression,” arXiv preprint, Nov. 2023, doi: 10.48550/arXiv.2311.05641.

B. Chen, J. Liang, N. Zheng, and J. C. Príncipe, “Kernel least mean square with adaptive kernel size,” Neurocomputing, vol. 191, pp. 95–106, 2016, doi: 10.1016/j.neucom.2016.01.004.

M. B. Adiguzel and M. A. Cengiz, “Model selection in multivariate adaptive regressions splines (MARS) using alternative information criteria,” Heliyon, vol. 9, no. 9, 2023.

R. Hidayat, I. N. Budiantara, B. W. Otok, and V. Ratnasari, “The Regression Curve Estimation by Using Mixed Smoothing Spline and Kernel (MsS-K) Model,” Commun. Stat. Theory Methods, vol. 50, no. 17, pp. 3942–3953, 2020, doi: 10.1080/03610926.2019.1710201.

R. Hidayat et al., “An Extended Model of Penalized Spline with The Addition of Kernel Functions in Nonparametric Regression Model,” Appl. Math. Inf. Sci., vol. 13, no. 3, pp. 453–460, 2019, doi: 10.18576/amis/130318.

F. Ronning, “The Role of Fourier Series in Mathematics and in Signal Theory,” Int. J. Res. Undergrad. Math. Educ., vol. 7, pp. 189–210, 2021, doi: 10.1007/s40753-021-00134-z.

I. Muda and A. A. F. Hutapea, “Influence of capital expenditure and income original region to the income per capita in Indonesia,” IOP Conf. Ser. Earth Environ. Sci., vol. 126, p. 012065, 2018, doi: 10.1088/1755-1315/126/1/012065.

X. Zhang and S. Rozelle, “Education Universalization, Rural School Participation, and Population Density,” China World Econ., vol. 30, no. 4, pp. 4–30, 2022, doi: 10.1111/cwe.12426.

R. Hidayat, I. N. Budiantara, B. W. Otok, and V. Ratnasari, “A Reproducing Kernel Hilbert Space Approach and Smoothing Parameters Selection In Spline-Kernel Regression,” J. Theor. Appl. Inf. Technol., vol. 97, no. 2, pp. 465–475, 2019.

R. Hidayat, M. Ilyas, and Y. Yuliani, “Spline model in the case of cervical cancer patient resilience,” Trends in Sciences, vol. 20, no. 8, pp. 6170–6180, 2023.

DOI: https://doi.org/10.37905/euler.v13i2.33062