DefinePK hosts the largest index of Pakistani journals, research articles, news headlines, and videos. It also offers chapter-level book search.
Title: Simplification of correspondence analysis for more precise calculation which one qualitative variables is two categorical data
Authors: I. Ginanjar, U.S. Pasaribu, A. Barra
Journal: ARPN Journal of Engineering and Applied Sciences
Publisher: Khyber Medical College, Peshawar
Country: Pakistan
Year: 2016
Volume: 11
Issue: 3
Language: English
The calculations of correspondence analysis (CA) are using the long stages matrix operations, so that through many times rounding process, and the Eigenvalues obtained by numerical process. The CA is often using standard residual matrix to calculate the singular value decomposition (SVD), this paper proves that 0 is a singular value of standard residual matrix. Based on that, this paper introduce simplification of correspondence analysis (SoCA) of 2×H contingency table where H=2, 3, 4,?, where obtain the simpler and more precise calculation, because it managed to minimize rounding process, also does not use the numerical process, with use standardized residuals matrix as a matrix to calculate the SVD, it is very useful for data mining techniques.
Loading PDF...
Loading Statistics...