Skip to main content Skip to main navigation menu Skip to site footer
Articles
Published: 2019-12-31

Analisis Masalah Heteroskedastisitas Menggunakan Generalized Least Square dalam Analisis Regresi

Classical Assumption Violation Estimator Effectiveness Generalized Least Square Ordinary Least Square Regression Analysis

Abstract

Regression analysis is one statistical method that allows users to analyze the influence of one or more independent variables (X) on a dependent variable (Y).The most commonly used method for estimating linear regression parameters is Ordinary Least Square (OLS). But in reality, there is often a problem with heteroscedasticity, namely the variance of the error is not constant or variable for all values of the independent variable X. This results in the OLS method being less effective. To overcome this, a parameter estimation method can be used by adding weight to each parameter, namely the Generalized Least Square (GLS) method. This study aims to examine the use of the GLS method in overcoming heteroscedasticity in regression analysis and examine the comparison of estimation results using the OLS method with the GLS method in the case of heteroscedasticity.The results show that the GLS method was able to maintain the nature of the estimator that is not biased and consistent and able to overcome the problem of heteroscedasticity, so that the GLS method is more effective than the OLS method.

References

  1. Adani dan Widodo, 2016, Perbandingan Kemampuan Regresi Kuantil Median dan Transformasi Box-Cox dalam Mengatasi Heteroskedastisitas, Konferensi Nasional Penelitian Matematika dan Pembelajarannya (KNPMP I), Universitas Muhammadiyah Surakarta, 12 Maret 2016.
  2. Algifari, 2000, Analisis Regresi: Teori, Kasus dan Solusi, Edisi kedua, BPFE-Yogyakarta, Yogyakarta.
  3. Gujarati, D.N., 2004, Basic Econometric, Mc Graw Hill, New York.
  4. Iswati, Helmi, Rahmat Syahni, dan Maiyastri, 2014, Perbandingan Penduga Ordinary Least Square (OLS) dan Generalized Least Square (GLS) Pada Model Regresi Linier dengan Regresor Bersifat Stokastik dan Galat Model Berautokeralas, Jurnal Matematika UNAND Vol.3 No.4 Hal.168-176.
  5. Nachrowi, Djalal, dan Hardius Usman, 2006, Pendekatan Populer dan Praktis Ekonometrika Untuk Analisis Ekonomi dan Keuangan, FEUI.
  6. Quadratullah, M. 2012, Analisis Regresi Terapan Teori, Contoh Kasus, dan Aplikasi dengan SPSS, ANDI, Yogyakarta.
  7. Suliyanto, 2011, Ekonometri Terapan : Teori dan Aplikasi dengan SPSS, Andi Yogyakarta, Purwokerto.
  8. Uthami, dkk., 2013, Regresi Kuantil Median untuk Mengatasi Heteroskedastisitas pada Analisis Regresi, E-Jurnal Matematika Vol.2, No.1, Januari 2013, 6-13.

How to Cite

R, A. S., Hadijati, M., & Switrayni, N. W. (2019). Analisis Masalah Heteroskedastisitas Menggunakan Generalized Least Square dalam Analisis Regresi. EIGEN MATHEMATICS JOURNAL, 1(2), 61–72. https://doi.org/10.29303/emj.v1i2.43