Pemodelan Produksi Padi di Provinsi Jawa Timur dengan Regresi Non Parametrik B-Spline

Sri Sulistijowati Handajani, Program Studi Statistika, Universitas Sebelas Maret, Surakarta, Indonesia
Hasih Pratiwi, Program Studi Statistika, Universitas Sebelas Maret, Surakarta, Indonesia
Yuliana Susanti, Program Studi Statistika, Universitas Sebelas Maret, Surakarta, Indonesia
Respatiwulan Respatiwulan, Program Studi Statistika, Universitas Sebelas Maret, Surakarta, Indonesia
Muhammad Bayu Nirwana, Program Studi Statistika, Universitas Sebelas Maret, Surakarta, Indonesia
Arik Mahmudah, Program Studi Statistika, Universitas Sebelas Maret, Surakarta, Indonesia

Abstract


Kebutuhan pangan merupakan kebutuhan primer masyarakat yang harus terpenuhi. Makanan pokok yang banyak dikonsumsi masyarakat Indonesia salah satunya beras. Beras yang berasal dari padi selalu diusahakan memenuhi untuk kebutuhan konsumsi masyarakat terutama di sekitarnya. Jawa Timur adalah salah satu provinsi penyumbang terbesar produksi padi di Indonesia.  Oleh sebab itu perlunya melihat pengaruh faktor-faktor iklim di beberapa wilayah produksi padi terbesar di provinsi Jawa Timur yaitu kabupaten Tuban, Nganjuk dan Gresik terhadap besarnya produksi padi di wilayah tersebut. Tujuan penelitian ini adalah menganalisis faktor-faktor meliputi suhu, kelembaban, curah hujan dan luas panen padi terhadap jumlah prodiksi padi. Data diambil dari website BMKG dan BPS tahun 2020-2022 di Kabupaten Tuban, Nganjuk dan Gresik. Metode analisis yang digunakan dengan memodelkan regresi non parametrik B-spline dengan beberapa kombinasi titik knot dari beberapa variable prediktor yang menghasilkan GCV terkecil dari kemungkinan banyaknya titik knot yang dicobakan. Hasil pemodelan mendapatkan knot optimum pada variabel X1 (suhu) berorde 2 dengan tiga titik knot bernilai 23,45584; 24,32467; 26,93116. Knot optimum pada variabel X2 (kelembaban) berorde 2 dengan satu titik knot bernilai 83,3828. Knot optimum pada variabel X3 (curah hujan) berorde 2 dengan dua titik knot bernilai 5,177247 dan 15,51238. Knot optimum pada variabel X4 (luas panen padi) berorde 2 dengan satu titik knot bernilai 16939,25. Nilai GCV minimum yang diperoleh adalah 18462458. Hasil analisis menunjukkan semua variable berpengaruh signifikan walaupun untuk variable iklim terdapat beberapa segmen yang kurang signifikan, dengan nilai adjusted R-Square sebesar 0,987.

 

The need for food is a primary requirement of society that must be fulfilled. One of the staple foods widely consumed by the Indonesian society is rice. Rice, which comes from paddy fields, is always cultivated to fufill  the consumption needs of the community, especially in the surrounding areas. East Java is one of the largest contributors to rice production in Indonesia. Therefore, it is necessary to examine the influence of climate factors in several rice-producing regions in East Java, namely Tuban, Nganjuk, and Gresik regencies, on the level of rice production in those areas. The aim of this research is to analyze factors such as rainfall, humidity, temperature, and rice cultivation area on rice production quantity.  The data was collected from BMKG (Meteorology, Climatology, and Geophysics Agency) and BPS (Central Statistics Agency) websites for the years 2020-2022 in Tuban, Nganjuk, and Gresik regencies. The analysis method used involves modeling non-parametric B-splines with various combinations of knot points from multiple predictor variables, resulting in the smallest Generalized Cross-Validation (GCV) among the possible knot points tested. The modeling results obtained the optimal knots for variable X1 (temperature) of order 2 with three knot points at values 23.45584, 24.32467, and 26.93116. The optimal knot for variable X2 (humidity) of order 2 was at one knot point with a value of 83.3828. The optimal knots for variable X3 (rainfall) of order 2 were two knot points with values of 5.177247 and 15.51238. The optimal knot for variable X4 (rice cultivation area) of order 2 was at one knot point with a value of 16,939.25. The minimum GCV value obtained was 18,462,458. The analysis results indicate that all variables have a significant influence, although for climate variables, there were some segments that were less significant, with an value adjusted R-Square of 0.987.


Keywords


GCV; produksi padi; regresi B-Spline; titik knot

Full Text:

PDF

References


Antoniadis, A., Bigot, J., & Spatinas, T. (2001). Wavelet estimators in nonparametric regression: a comparative simulation study. Journal of Statistical Software, 6, 1–83. https://doi.org/10.18637/jss.v006.i06

Badan Pusat Statistik (BPS). (2020). Badan Pusat Statistik Indonesia. https://www.bps.go.id/id.

Badan Pusat Statistik Provinsi Jawa Timur (BPS Jawa Timur). (2023). Badan Pusat Statistik Provinsi Jawa Timur. jatim.bps.go.id.

Data Online Pusat Database BMKG. (2023). Data Online Database BMKG Provinsi Jawa Timur. https://dataonline.bmkg.go.id/home

Becher, H., Kauermann, G., Khomski, P., & Kouyate, B. (2009). Using penalized splines to model age and season of birth dependent effects of childhood mortality risk factors in rural burkina faso. Biometrical Journal, 51, 110–122. https://doi.org/10.1002/bimj.200810496

Bidayani, B., Hadijati, M., & Fitriyani, N. (2019). Model regresi semiparametrik spline hasil produksi padi di Kabupaten Lombok Timur. EIGEN MATHEMATICS JOURNAL, 2(1), 11–17. https://doi.org/10.29303/emj.v1i1.31

Chamidah, N., Gusti, K. H., Tjahjono, E., & Lestari, B. (2019). Improving of classification accuracy of cyst and tumor using local polynomial estimator. TELKOMNIKA (Telecommunication Computing Electronics and Control), 17(3), 1492–1500. https://doi.org/10.12928/telkomnika.v17i3.12240

Chamidah, N., & Lestari, B. (2019). Estimation of covariance matrix using multi-response local polynomial estimator for designing children growth charts: A theoretically discussion. Journal of Physics: Conference Series, 1397(1). https://doi.org/10.1088/1742-6596/1397/1/012072

Chamidah, N., Lestari, B., & Saifudin, T. (2019). Modeling of blood pressures based on stress score using least square spline estimator in bi-response nonparametric regression. International Journal of Innovation, Creativity and Change, 5(3). https://www.ijicc.net/images/Vol_5_Iss_3/Part_2_2020/5321_Chamidah_2019_E_R.pdf

Cox, D. D., & O’Sullivan, F. (1996). Penalized type estimator for generalized nonparametric regression. Journal of Multivariate Analysis, 56, 185–206. https://doi.org/10.1006/jmva.1996.0010

Eberly, D. (1999). B-Splines interpolation on Lattices. https://www.geometrictools.com/Documentation/BSplineInterpolation.pdf

Eubank, R. L. (1999). Nonparametric Regression and Spline Smoothing. Marcel Dekker Inc.

Fatmawati, F., Budiantara, I. N., & Lestari, B. (2019). Comparison of smoothing and truncated spline estimators in estimating blood pressures models. International Journal of Innovation, Creativity and Change, 5(3), 1177–1199. https://www.ijicc.net/images/Vol_5_Iss_3/Part_2_2020/5320_Fatmawati_2019_E_R.pdf

Huang, J. Z., & Liu, L. (2006). Polynomial spline estimation and inference of proportional hazards regression models with flexible relative risk form. Biometrics, 62, 793–802. https://doi.org/10.1111/j.1541-0420.2005.00519.x

Handajani, S. S., Pratiwi, H., Respatiwulan, Qona'ah, N., Ramadhania, M., Evitasari, N., Apsari, N. E. (2023). Comparison of B-spline and truncated spline regresion models for temperature forecast. Journal of Mathematics and Its Applications, 17(4), 1969-1984. https://doi.org/10.30598/barekengvol17iss4pp1969-1984

Kayri, M., & Zirhhoglu, G. (2009). Kernel smoothing function and choosing bandwidth for nonparametric regression methods. Ozean Journal of Applied Sciences, 2, 49–60. https://www.semanticscholar.org/paper/KERNEL-SMOOTHING-FUNCTION-AND-CHOOSING-BANDWIDTH-Kayri-Z%C4%B1rhl%C4%B1o/b9aa75efe9bdaaa4131f2c209a865ad14021d326

Khan, A., & Shahna, S. (2019). Non-polynomial quadratic spline method for solving fourth order singularly perturbed boundary value problems. Journal of King Saud University - Science, 31(4), 479–484. https://doi.org/10.1016/j.jksus.2017.08.006

Koenker, R. Ng., P., & Portnoy, S. (1994). Quantile smoothing splines. Biometrika, 81(4). https://doi.org/10.2307/2337070

Lestari, B., Budiantara, I. N., Sunaryo, S., & Madhuri, M. (2010). Spline estimator in-multi response nonparametric regression model. Journal of Mathematics and Statistics2, 6, 327–332. https://jurnal.unej.ac.id/index.php/JID/article/view/102/74

Lestari, B., Chamidah, N., Aydin, D., & Yilmaz, E. (2022). Reproducing kernel hilbert space approach to multiresponse smoothing spline regression function. Symmetry, 14(11), 2227. https://doi.org/10.3390/sym14112227

Lestari, B., Fatmawati, F., & Budiantara, I. N. (2020). Spline estimator and its asymptotic properties in multiresponse nonparametric regression model. Songklanakarin Journal Od Science and Technology, 42(3), 533–548. https://doi.org/10.14456/sjst-psu.2020.68

Lestari, B., Fatmawati, F., Budiantara, I. N., & Chamidah, N. (2018). Estimation of regression function in multi-response nonparametric regression model using smoothing spline and kernel estimators. Journal of Physics: Conference Series, 1097, 012091. https://doi.org/10.1088/1742-6596/1097/1/012091

Lestari, B., Fatmawati, F., Budiantara, I. N., & Chamidah, N. (2019). Smoothing parameter selection method for multiresponse nonparametric regression model using smoothing spline and Kernel estimators approaches. Journal of Physics: Conference Series, 1397(1), 012064. https://doi.org/10.1088/1742-6596/1397/1/012064

Lyche, T., & Morken, K. (2008). Spline Methods. Retrieved September 6, 2022, from https://www.uio.no/studier/emner/matnat/ifi/nedlagte-emner/INF-MAT5340/v10/undervisningsmateriale/book.pdf

Oehlert, G. W. (1992). Relaxed boundary smoothing spline. The Annals of Statistics, 20(1146–1160). http://www.jstor.org/stable/2242154

Osmani, F., Hajizadeh, E., & Mansouri, P. (2019). Kernel and regression spline smoothing techniques to estimate coefficient in rates model and its application in psoriasis. Medic. J. Islamic Rep. Iran, 33(90), 1–5. https://doi.org/10.34171/mjiri.33.90

Shahna, S., & Khan, A. (2019). Approximations for higher order boundary value problems using non-polynomial quadratic spline based on off-step points. Journal of King Saud University - Science, 31(4), 737–745. https://doi.org/10.1016/j.jksus.2018.06.004

Valentina, M. F. (2022). Pemodelan kemiskinan di jawa timur menggunakan regresi nonparametrik B-spline. Surabaya: Universitas Islam Negeri Sunan Ampel. http://digilib.uinsa.ac.id/id/eprint/52923

Wahba, G. (1990). Spline models for observation data. In SIAM Pennsylvania. https://doi.org/10.1137/1.9781611970128

Wu, H., & Zhang, J. T. (2006). Nonparametric Regression Method for Longitudinal Data Analysis: Mixed Effects Modeling Approaches. John Wiley and Sons.

Wulandari, I. D., & Budiantara, I. N. (2014). Analisis faktor-faktor yang mempengaruhi persentase penduduk miskin dan pengeluaran perkapita makanan di jawa timur menggunakan regresi nonparametrik biresponden spline. Jurnal Sains Dan Seni POMITS, 3(1). https://doi.org/10.12962/j23373520.v3i1.6110




DOI: https://doi.org/10.21831/pythagoras.v18i2.67475

Refbacks

  • There are currently no refbacks.


PYTHAGORAS: Jurnal Matematika dan Pendidikan Matematika indexed by:


Creative Commons License Pythagoras is licensed under a Creative Commons Attribution 4.0 International License.
Based on a work at http://journal.uny.ac.id/index.php/pythagoras.

All rights reserved p-ISSN: 1978-4538 | e-ISSN: 2527-421X

Visitor Number:

View Pythagoras Stats