search for




 

Prediction of PM10 in Seoul using penalized regression†
Journal of the Korean Data & Information Science Society 2021;32:631-40
Published online May 31, 2021;  https://doi.org/10.7465/jkdi.2021.32.3.631
© 2021 Korean Data and Information Science Society.

Jisu Won1 · Jonghwa Na2

1Korea Disease Control and Prevention Agency
2Department of Information and Statistics, Chungbuk National University
Correspondence to: This research was supported by Chungbuk National University Korea National University Development Project(2020).
1 Researcher, Korea Disease Control and Prevention Agency (KDCA), Chungbuk 28159.
2 Corresponding author: Professor, Department of Information & Statistics, Chungbuk National University, Chungbuk 28644, Korea. E-mail: cherin@chungbuk.ac.kr
Received March 19, 2021; Revised April 16, 2021; Accepted April 19, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The recent rapid increase in domestic fine dust(PM10) has a great impact on daily life and public health. The problem of determining the cause of and predicting about PM10 has been carried out by many researchers, but has not been able to present a clear solution. In this study, various methods of penalized regression using meteorological and environmental factors as predictors were proposed for the prediction of PM10. In particular, in this study, information of weather and environment-related predictors up to 15 days ago was used. The problem of multicollinearity arises between the predictors at the previous point in time. As a solution to this, in this paper, the method of penalized regression is applied. Lasso, adaptive lasso, SCAD and MCP were applied as the penalty regression, and data from Seoul city were used for analysis.
Keywords : Cross validation, MCP, penalized regression, SCAD.