Beta 1

Title Statistical Analysis of Phytoplankton
Author Fan, Hua
Supervisor Rootzen, Helle (Mathematical Statistics, Department of Informatics and Mathematical Modeling, Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark)
Carstensen, Niels Jacob (Department of Environmental Science and Engineering, Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark)
Institution Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark
Thesis level Master's thesis
Year 2008
Abstract Eutrophication in coastal waters is the cause of growth in phytoplankton which can lead to shading out of benthic vegetation and oxygen depletion. Experimental studies and theoretical considerations of growth strategies, have shown that changing nutrient levels should affect the phytoplankton composition, but no real case studies have been done to support these theories. By using data spanning two decades, from 30 stations based on the coast of Denmark, statistical models are created to show the phytoplankton response to total nitrogen and total phosphorous and to identify those species with high responsiveness to changing nutrient levels. The models are primary based on generalized linear model theory, and crossvalidation is used to assess the models’ goodness-of-fit. Other statistical methods, Ward’s minimum-variance, response surface plot, contour plot, power analysis and principal components analysis are also applied to find the common features for the variables and explore the relationships among them.
Series IMM-M.Sc.-2008-69
Original PDF ep08_69.pdf (10.54 MB)
Admin Creation date: 2008-07-17    Update date: 2008-07-17    Source: dtu    ID: 221844    Original MXD