Title :
Parallel factoring of strata
Author_Institution :
Inst. of Math., Budapest Univ. of Technol. & Econ., Hungary
Abstract :
A method for compromise factor extraction from covariance/correlation matrices corresponding to different strata is introduced. Compromise factors are independent and on this constraint they explain the largest possible part of the variables´ total variance over the strata. Binary samples are also investigated. The so-called compromise representation of the strata is introduced. A practical application for parallel factoring of medical data in different strata is also presented.
Keywords :
covariance matrices; data analysis; medical computing; normal distribution; binary samples; compromise factor extraction; correlation matrices; covariance matrices; medical data; normal distribution; strata parallel factoring; Artificial intelligence; Covariance matrix; Data mining; Data structures; Information technology; Laplace equations; Mathematics; Medical services; Stochastic processes; Symmetric matrices;
Conference_Titel :
Information Technology Interfaces, 2001. ITI 2001. Proceedings of the 23rd International Conference on
Print_ISBN :
953-96769-3-2
DOI :
10.1109/ITI.2001.938028
