Premium
Analyses of Species Densities by the Multivariate General Linear Model
Author(s) -
Buzas Martin A.
Publication year - 1971
Publication title -
limnology and oceanography
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.7
H-Index - 197
eISSN - 1939-5590
pISSN - 0024-3590
DOI - 10.4319/lo.1971.16.4.0667
Subject(s) - multivariate statistics , a priori and a posteriori , multivariate analysis , linear model , general linear model , mathematics , statistics , environmental science , ecology , biology , philosophy , epistemology
A multivariate general linear model was constructed a priori to analyze observed species densities for three species of Foraminifera at 3 stations in the Choptank River, Maryland. The model contained 21 parameters for environmental variables, station differences, overall periodicity, and interaction of periodicity and station differences. Several more restricted models were postulated and compared with the general model. None of the more restricted models adequately explained the data. The high degree of complexity indicates that large complex models will be needed to explain observed species densities.