Mean Imputation Techniques for Filling the Missing Observations in Air Pollution Dataset

M.N. Noor; A.S. Yahaya; N.A. Ramli; A.M. Mustafa Al Bakri

doi:10.4028/www.scientific.net/KEM.594-595.902

Paper Titles

Preparation of Polyethersulfone Ultrafiltration Membrane Surface Coated with TiO₂Nanoparticles and Irradiated under UV Light
p.877

Effect of Volume Plasticizers on the Thermal Performance of Tacca leontopetaloides Starch Biopolymer
p.882

Filling Missing Data Using Interpolation Methods: Study on the Effect of Fitting Distribution
p.889

Evaluation Grain Homogeneity of Aluminium after ECAP Process by ECAP Geometry Analysis Using Taguchi Method
p.896

Mean Imputation Techniques for Filling the Missing Observations in Air Pollution Dataset
p.902

Compressive Behavior of AA6061 at Room Temperature and Validation of the FE Model Based on Optical 3D Measurement Technique
p.909

Photovoltaic Powered Uninterruptible Power Supply Using Microcontroller PIC16F628-I/P
p.914

Design and Development of Tracking System for Mines Detector Robot
p.919

Design and Development of Sensing System for Mines Detector Robot
p.924

HomeKey Engineering MaterialsKey Engineering Materials Vols. 594-595Mean Imputation Techniques for Filling the Missing...

Mean Imputation Techniques for Filling the Missing Observations in Air Pollution Dataset

Abstract:

Almost all real life datasets consist missing values. These are usually due to machine failure, routine maintenance, changes in siting monitors and human error. The occurence of missing values requires special attention on analysing the data. Incomplete datasets can cause bias due to systematic differences between observed and unobserved data. Therefore, the need to find the best way in estimating missing values is very important so that the data analysed is ensured of high quality. In this research, three types of mean imputation techniques that are mean, mean above and mean above below methods were used to replace the missing values. Annual hourly monitoring data for PM₁₀ were used to generate missing values. Four randomly simulated missing data were evaluated in order to test the efficiency of the methods used. They are 5%, 10%, 15%, 25% and 40%. Three types of performance indicators that are mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R²) were calculated to describe the goodness of fit for all the method. From all the method applied, it was found that mean above below method is the best method for estimating data for all percentages of simulated missing values.

You might also be interested in these eBooks

Advanced Materials Engineering and Technology II

View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 594-595)

Pages:

902-908

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.594-595.902

Citation:

Cite this paper

Online since:

December 2013

Authors:

M.N. Noor, A.S. Yahaya, N.A. Ramli, A.M. Mustafa Al Bakri

Keywords:

Air Pollution, Imputation, Performance Indicators, PM₁₀

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Hawthorne, G. and Elliot, P. (2005). Imputing Cross-Sectional Missing Data: Comparison of Common Techniques. Australian and New Zealand Journal of Psychiatry 39, 583-590.

DOI: 10.1080/j.1440-1614.2005.01630.x

Google Scholar

[2] Junninen, H., Niska, H., Tuppurrainen, K., Ruuskanen, J., Kolehmainen, M., (2004). Methods for Imputation of Missing Values in Air Quality Data Sets. Journal of Atmospheric Environment 38, 2895-2907.

DOI: 10.1016/j.atmosenv.2004.02.026

Google Scholar

[3] SPSS Incorporated, (2000). SPSS Reference Guide. Chicago: SPSS Inc.

Google Scholar

[4] Yahaya, A.S., Ramli, N.A. and Yusof, N.F., (2005).

Google Scholar