Open AccessComparison of Partial Least Squares Regression and Principal Component Regression for Overcoming Multicollinearity in Human Development Index Model
Author(s) -
Ravika Dewi Samosir,
Deiby Tineke Salaki,
Yohanes Langi
Publication year - 2022
Publication title -
operations research international conference series/operations research.international conference series
Language(s) - English
Resource type - Journals
eISSN - 2723-1739
pISSN - 2722-0974
DOI - 10.47194/orics.v3i1.126
Subject(s) - multicollinearity , principal component regression , principal component analysis , statistics , ordinary least squares , partial least squares regression , variance inflation factor , mathematics , regression analysis , regression , econometrics , robust regression , linear regression , index (typography) , computer science , world wide web
One of the assumptions in ordinary least squares (OLS) in estimating regression parameter is lack of multicollinearity. If the multicollinearity exists, Partial Least Square (PLS) and Principal Component Regression (PCR) can be used as alternative approaches to solve the problem. This research intends to compare those methods in modeling factors that influence the Human Development Index (HDI) of North Sumatra Province in 2019 obtained from the Central Bureau of Statistics. The result indicates that the PLS outperforms the PCR in term of the coefficient of determination and squared error