Документ взят из кэша поисковой машины. Адрес оригинального документа : http://www.sao.ru/precise/Midas_doc/doc/94NOV/vol2/node30.html
Дата изменения: Fri Feb 23 14:02:24 1996
Дата индексирования: Tue Oct 2 17:24:53 2012
Кодировка:

Поисковые слова: п п п п п п п р п р р п п р п р п п р п р п п р п
Multivariate Statistical Methods



next up previous contents
Next: CCD Reductions Up: Analysis of Results Previous: Statistical Tests

Multivariate Statistical Methods

When the analysis yields a large number of parameters for each object, it is difficult to overview relations between the individual variable. Multivariate statistical methods can be applied in such a situation to give an objective description of the data. The Principal Components Analysis is used to determine the true dimensionality of the data set and find the best linear combination of the parameter for following studies (see Chatfield and Collins 1980). A typical example of such analysis was performed by Okamura (1985) on photometric data from Virgo Cluster galaxies.

Structures and groups in large data sets can be located by means of a Cluster Analysis which constructs a set of groups in the data using a given distance measure. A large variety of methods for clustering are available with different distance definitions providing both hierarchical and non--hierarchical groups (see Murtagh 1986 and references therein). These techniques are used especially for classification problems in astronomy.

References



next up previous contents
Next: CCD Reductions Up: Analysis of Results Previous: Statistical Tests



Pascal Ballester
Tue Mar 28 16:52:29 MET DST 1995