Factor analysis of incidence data via novel decomposition of matrices

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F09%3A00010281" target="_blank" >RIV/61989592:15310/09:00010281 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Factor analysis of incidence data via novel decomposition of matrices
Original language description
Matrix decomposition methods provide representations of anobject-variable data matrix by a product of two different matrices, onedescribing relationship between objects and hidden variables or factors,and the other describing relationship between the factors and the originalvariables. We present a novel approach to decomposition and factoranalysis of matrices with incidence data. The matrix entries are gradesto which objects represented by rows satisfy attributes represented bycolumns, e.g. grades to which an image is red or a person performs wellin a test. We assume that the grades belong to a scale bounded by 0and 1 which is equipped with certain aggregation operators and forms acomplete residuated lattice. We present an approximation algorithm forthe problem of decomposition of such matrices with grades into productsof two matrices with grades with the number of factors as smallas possible. Decomposition of binary matrices into Boolean products ofbinary matrices is a special case of
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
BD - Information theory
OECD FORD branch
—

Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)