The course Multivariate Analysis offers a thorough introduction to multivariate statistical methods, tailored for researchers working with complex datasets where multiple variables are measured simultaneously. It is particularly relevant for those analysing data from fields such as ecology, agriculture, environmental sciences, and related disciplines, where observations often include numerous interdependent variables.
Participants will learn to address challenges common in such datasets, including multicollinearity, high dimensionality, and the need for effective visualization. Key topics include principal component analysis, redundancy analysis, correspondence analysis, clustering, and other ordination methods, alongside foundational techniques like multiple linear regression, logistic regression, and loglinear models. These regression-based methods are essential for understanding relationships between variables, modelling outcomes, and handling categorical data.
The course balances theoretical insights with practical applications, emphasizing the importance of selecting appropriate techniques to answer specific research questions. Participants will explore how to uncover patterns, reduce dimensionality, and interpret complex relationships within their data. Special focus is given to methods for visualizing multivariate results and communicating findings effectively. Through interactive lectures and hands-on exercises, participants will gain the skills to apply multivariate techniques. By the end of the course, they will be well-prepared to analyse their own data, whether it involves exploring ecological gradients, studying community composition, interpreting multi-response agricultural trials, or modelling complex systems using regression approaches.
| Day 1 | Collecting data, multiple linear regression and polynomials, qualitative variables in regression, selection of variables, comparing models. |
| Day 2 | Loglinear models, analysis of presence-absence data, logistic regression analyses with the Gaussian response model. |
| Day 3 | Introduction to multivariate analysis, ordination, direct and indirect analysis of gradients, length of gradient, principal components analysis (PCA), redundancy analysis (RDA), interpretation biplots of PCA and RDA. |
| Day 4 | Ordination based on correspondence analysis methods (CA, CCA and DCA) Interpretation CA/DCA plots, choice of method. |
| Day 5 | Cluster analysis, choice of similarity measure, agglomerative methods, divisive methods, classification and interpretation. |
| Target Group | The course is aimed at PhD candidates, postdocs, and other academics that are working above plant integration level in plant, animal, and/or environmental/ecological sciences |
| Group Size | Max. 24 participants |
| Course duration | 5 days |
| Prior knowledge | Participants are expected to have a good knowledge of basic statistics (like hypothesis testing, t- and F-tests and linear regression) and some experience in a statistical package (GenStat, R, SPSS, or likewise) |
| Lecturers | Ir. Saskia Burgers (Wageningen UR) and dr. Jos Hageman (Biometris, Wageningen UR) |
| FEE1 | |
| PE&RC/WIMEK/EPS/WASS/VLAG/WIAS PhD candidates with approved TSP and WU EngD candidates | € 265,- |
| PE&RC postdocs and staff | € 530,- |
| All other academic participants | € 570,- |
| Non-academic participants | € 1100,- |
1 The course fee includes a reader, coffee/tea, and lunches. It does not include accommodation.
Note:
PE&RC Cancellation Conditions
IMPORTANT: ALWAYS read the Cancellation conditions for PE&RC courses and activities.
