Analysis of Factors that Influence Poverty in West Nusa Tenggara Using Principal Component Regression

Lisa Harsyiah; Zulhan Widya Baskara; Dina Eka Putri; Rifdah Fadhilah

doi:10.29303/emj.v8i1.229

Authors

Lisa Harsyiah Department of Statistics, Universitas Mataram
Zulhan Widya Baskara Department of Statistics, Universitas Mataram
Dina Eka Putri Department of Statistics, Universitas Mataram
Rifdah Fadhilah Department of Mathematics, Universitas Mataram

DOI:

https://doi.org/10.29303/emj.v8i1.229

Keywords:

Poverty, Multicollinearity, Principal Component Regression

Abstract

West Nusa Tenggara (NTB) is one of the provinces in Indonesia with a percentage of poor people according to the March-September period in 2019, namely 14.56% -13.88%, while in 2020 it was 13.97% -14.23% and in 2021 the percentage was 14.14% -13.83%. The factors suspected of influencing poverty in each province have different conditions each year, so repeated observations are needed on poverty data and the factors that influence it. If the data contains multicollinearity, then one of the classic assumptions of multiple linear regression is not met so that the problem of multicollinearity needs to be addressed. The Principal Component Regression (PCR) method is the most consistent compared to the ridge and least square regression methods in solving multicollinearity problems. This study aims to analyze poverty in NTB using the PCR method. The data used in this study are the number of poor people and factors influencing poverty based on districts in NTB in 2020-2022. Based on the calculation results, it was obtained that Component 1 with an eigenvalue of 4.008 explained 57.2% of the variance, while Component 2 with an eigenvalue of 1.740 explained 82.1% of the variance. Both components significantly affect poverty according to the results of simultaneous and partial tests. This model has an R^2 value of 0.302 or 30.2% and the remaining 69.8% is influenced by external factors (error). The R^2 value is classified as a weak category and it is recommended to add other factors that affect poverty including access to electricity, access to sanitation, access to clean drinking water, and government spending.

References

R. Rahmawati, L. Harsyiah, and Z. Baskara, “Comparison of ridge regression and principal component regression in overcoming multicollinearity of factors affecting poverty in indonesia,” in International Conference on Mathematics:Pure, Applied and Computation, pp. 41–51, Springer, 2023. https://doi.org/10.1007/978-981-97-2136-8 4.

D. N. Gujarati, Basic Econometrics. Boston: McGraw Hill, 4th ed ed., 2003.

A. Astuti, Partial Least Square (PLS) and Principal Component Regression (PCR) for Linear Regression with Multicollinearity in the Case of the Human Development Index in Gunung Kidul Regency. PhD thesis, Universitas Negeri Yogyakarta, Yogyakarta, 2014.

S. Pujilestari, N. Dwidayati, and S. , “Pemilihan Model Regresi Linier Berganda Terbaik pada Kasus Multikolinieritas berdasarkan Metode Principal Component Analysis (PCA) dan Metode Stepwise,” UNNES Journal of Mathematics, vol. 6, no. 1, pp. 61–71, 2017. https://journal.unnes.ac.id/sju/ujm/article/view/11719.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. Springer Series in Statistics, New York, NY: Springer New York, 2009. https://doi.org/10.1007/978-0-387-84858-7.

N. Herawati, K. Nisa, E. Setiawan, N. , and T. , “Multicollinearity, LASSO, Ridge Regression, Principal Component Regression,” International Journal of Statistics and Applications, vol. 8, pp. 167–172, 2018. http://article.sapub.org/10.5923.j.statistics.20180804.02.html.

D. C. Montgomery, E. A. Peck, and G. G. Vining, Introduction to linear regression analysis. John Wiley & Sons, 2021. https://www.kwcsangli.in/uploads/3--Introduction to Linear Regression Analysis 5th ed. Douglas C. Montgomery Elizabeth A. Peck and G. .pdf.

S. Çankaya, S. Eker, and S. H. Abacı, “Comparison of Least Squares, Ridge Regression and Principal Component Approaches in the Presence of Multicollinearity in Regression Analysis,” Turkish Journal of Agriculture – Food Science and Technology, vol. 7, no. 8, pp. 1166–1172, 2019. https://doi.org/10.24925/turjaf.v7i8.1166-1172.2515.

S. N. B. Sitepu, T. Haryanto, and N. M. Sukartini, “Faktor-Faktor Yang Mempengaruhi Persentase Penduduk Miskin Pulau Jawa-Bali dan Nusa Tenggara Barat,” PROSENAMA, vol. 2, no. 1, pp. 103–113, 2022. https://prosenama.upnjatim.ac.id/index.php/prosenama/article/view/32.

M. H. Kutner, C. Nachtsheim, J. Neter, and W. Li, eds., Applied Linear Statistical Models. The McGraw-Hill/Irwin Series Operations and Decision Sciences, Boston: McGraw-Hill Irwin, 5th ed ed., 2005.

N. R. Draper and H. Smith, Applied Regression Analysis. Wiley Series in Probability and Statistics, Wiley, 3 ed., 1998. https://onlinelibrary.wiley.com/doi/book/10.1002/9781118625590.

R. A. Johnson and D. W. Wichern, Applied Multivariate Statistical Analysis. Upper Saddle River, NJ: Pearson/Prentice Hall, 6. ed ed., 2007.

A. Mattjik and I. Sumertajaya, Sidik Peubah Ganda Dengan Menggunakan SAS. IPB PRESS, 2011.

I. Ghozali, Aplikasi Analisis Multivariete SPSS 23. Semarang: Badan Penerbit Universitas Diponegoro, 8 ed., 2016.

G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: With Applications in R. Springer Texts in Statistics, New York, NY: Springer US, 2021. https://link.springer.com/book/10.1007/978-1-4614-7138-7.

W. W. Chin, “The Partial Least Squares Approach to Structural Equation Modeling,” in Modern Methods for Business Research, Methodology for Business and Management, pp. 295–336, Mahwah, NJ, US: Lawrence Erlbaum Associates Publishers, 1998.