文章基本信息

标题：On the Number of Independent Components: An Adjusted Coefficient of Determination based Approach
本地全文：下载
作者：Saima Afzal ; Muhammad Mutahir Iqbal ; Ayesha Afzal 等
期刊名称：Electronic Journal of Applied Statistical Analysis
电子版ISSN：2070-5948
出版年度：2021
卷号：14
期号：1
页码：13-26
DOI：10.1285/i20705948v14n1p13
出版社：University of Salento
摘要：Independent Component Analysis (ICA) is a comparatively new statistical and computational technique to find hidden components from multivariate statistical data. The technique is also employed as a tool for dimension reduction for efficient data analysis. Reduction in dimensions can be done by assigning ranks to the independent components in some appropriate way and then restricting the data analysis to certain high ranking components only. The problem of determining the number of high ranked ICs that should be retained is the main objective of this paper. A method based upon adjusted coefficient of determination is proposed for the purpose. The performance of the proposed method is demonstrated through experimental evaluation on real-world financial time series data.
其他摘要：Independent Component Analysis (ICA) is a comparatively new statisticaland computational technique to find hidden components from multivariate statistical data. The technique is also employed as a tool for dimension reduction for efficient data analysis. Reduction in dimensions can be done byassigning ranks to the independent components in some appropriate way and then restricting the data analysis to certain high ranking components only.The problem of determining the number of high ranked ICs that should be retained is the main objective of this paper. A method based upon adjusted coefficient of determination is proposed for the purpose. The performance of the proposed method is demonstrated through experimental evaluation on real-world financial time series data.
关键词：Adjusted coefficient of determination;dimension reduction;financial time series;independent component analysis;multidimensional data;big data analytics