Treatment of outliers via interpolation method with neural network forecast performances

Wahir, N. A. and Nor, M. E. and Rusiman, M. S. and Gopal, K. (2017) Treatment of outliers via interpolation method with neural network forecast performances. Journal of Physics: Conference Series, 995. pp. 1-7. ISSN 1742-6588

[img] Text
AJ 2018 (305).pdf
Restricted to Registered users only
Download (877kB) | Request a copy

Abstract

Outliers often lurk in many datasets, especially in real data. Such anomalous data can negatively affect statistical analyses, primarily normality, variance, and estimation aspects. Hence, handling the occurrences of outliers require special attention. Therefore, it is important to determine the suitable ways in treating outliers so as to ensure that the quality of the analyzed data is indeed high. As such, this paper discusses an alternative method to treat outliers via linear interpolation method. In fact, assuming outlier as a missing value in the dataset allows the application of the interpolation method to interpolate the outliers thus, enabling the comparison of data series using forecast accuracy before and after outlier treatment. With that, the monthly time series of Malaysian tourist arrivals from January 1998 until December 2015 had been used to interpolate the new series. The results indicated that the linear interpolation method, which was comprised of improved time series data, displayed better results, when compared to the original time series data in forecasting from both Box-Jenkins and neural network approaches.

Item Type: Article
Uncontrolled Keywords: NIL
Subjects: Q Science > QC Physics > QC851-999 Meteorology. Climatology. Including the earth's atmosphere > QC980-999 Climatology and weather > QC994.95-999 Weather forecasting
Divisions: Faculty of Applied Science and Technology > Department of Mathematics and Statistics
Depositing User: UiTM Student Praktikal
Date Deposited: 20 Jan 2022 04:50
Last Modified: 20 Jan 2022 04:50
URI: http://eprints.uthm.edu.my/id/eprint/5684

Actions (login required)

View Item View Item