Multivariate Data Analysis (2018)

Welcome to Multivariate Data Analysis


Description:

In many applications data is acquired from multiple sources or is described by multiple variables. Within areas of signal and image processing, biomechanics, clinical decision support, bioinformatics, etc. there is an increasing need for analyzing various types of multivariate data containing both dependent (outcome/response) variables and independent (predictor) variables. Instead of analyzing the data by treating it as a task of multiple univariate problems the methods in this course fully encompasses the task as a single multivariate problem. In effect, the covariate nature of the data is analyzed by examining relationships among multiple variables at the same time. The content of the course will cover multivariate methods for statistical analysis, machine learning and test evaluation. The tentative course program is:

 

  • Probabilistic classification
    • Bayesian decision theory
    • Multivariate density
    • Non-parametric classification
      • Perceptron classifier
      • Support Vector Machines
      • Clustering
      • Neural networks
        • Three-layer NN
        • Deep learning
        • Data analysis and test evaluation
          • Dimensionality reduction
          • ROC analysis
          • Cross validation
          • Multivariate statistics
            • Multivariate analysis of variance
            • Multivariate repeated measures analysis of variance

                                                            

Literature

Duda, Hart, Stork, Pattern Classification, 2nd Edition, Wiley (book)

James, Witten, Hastie, Tibshirani, An Introduction to Statistical Learning, 7th printing, Springer (PDF)

Mayers, Chapter 14, Multivariate Analysis (PDF)

 

Prerequisites

Statistics, Matlab (basic skills), SPSS (basic skills).

 

Evaluation

Evaluation of the course will be based on active participation in the course including practical exercises in Matlab and SPSS.

Organizer: Associate Professor Lasse Riis Østergaard, email: lasse@hst.aau.dk, Associate Professor Carsten Dahl Mørch, email: cdahl@hst.aau.dk, Assistant Professor Alex Skovsbo Jørgensen, email: asj@hst.aau.dk


Lecturers: Organizers

ECTS: 2

Time: 26 September (8.15-12.00), 1 October (12.30 – 16.15), 8 October (12.30 – 16.15) and 23 October 2018 (8.15-12.00)

Place: Aalborg University, Fredrik Bajers Vej 7E, room E3-209

City: Aalborg

Number of seats:

Deadline: 05 September 2018

Important information concerning PhD courses We have over some time experienced problems with no-show for both project and general courses. It has now reached a point where we are forced to take action. Therefore, the Doctoral School has decided to introduce a no-show fee of DKK 5,000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately three months before start. This can hopefully also provide new students a chance to register for courses during the year. We look forward to your registrations.