Multivariate Data Analysis for Management Science
Credits |
---|
5 |
Holder |
Dr. Maren Ulm (HEC Liège -ULiège) |
Language |
English |
Location |
HEC Liège, Rue Louvrex 14, 4000 Liège |
Field |
Methods / Core Learning |
Course Description
Prerequisites:
- Basic course in probability (density, distribution, mean, variance)
- Introductory knowledge of open source software R or the willingness to learn it in autonomy during the period of the course
Remark: PhD candidates interested in the course are kindly asked to contact the course instructor as early as possible before the start of the course per email: m.ulm@uliege.be.
Description of the course:
Content:
- Repetition of the essential statistical concepts for multivariate data analysis
- Preparing the data for multivariate analysis (assumptions, data examination, …)
- Interdependence techniques: a. Factor Analysis / b. Principal Components Analysis / c. Cluster Analysis
- Dependence techniques: a. Multivariate Analysis of Variance / b. Multiple Discriminant Analysis
- Structural Equation Modeling
Note: this course will not explicitly cover linear regression nor generalized linear models. These methods are covered in several other courses of the doctorate school program.
Exercise classes:
During the first exercise class an introduction to working with the open-source software program R is given. In all subsequent exercise classes, the participants are asked to work on exercises implementing the theoretical concepts seen during the lecture with the help of the instructor.
Learning objectives:
The emphasis of this course is on the application and implementation of the methods to analyze data in a multivariate context. While mathematical and statistical theory is employed where necessary, the focus of the course will be on the adequate usage of these techniques. This covers checking the methods’ assumptions towards the data, the estimation of models and assessment of the goodness of fit, as well as the interpretation and validation of the results.
At the end of the course, the participant is able to:
– identify the correct method to address a particular research question
– understand and independently implement the different steps of applying a multivariate data analysis
Assessment:
- A case study conducting a multivariate data analysis in the participant’s academic field of interest (70%)
- Oral presentation of the case study before submission (30%)
References:
- Everitt B., Hothorn T. (2011) An Introduction to Applied Multivariate Analysis with R, Springer
- Haerdle W., Simar L. (2015) Applied Multivariate Statistical Analysis, Springer
- Hair J.F., Black W., Babin B., Anderson R. (2019) Multivariate Data Analysis, Pearson
Schedule
Academic Year 2023-2024
- Thursday & Friday, October 26 and October 27, 9 am – 1 pm
- Thursday & Friday, November 9 and November 10, 9 am – 1 pm
- Thursday & Friday, November 16 and November 17, 9 am – 1 pm
- Thursday & Friday, November 23 and November 24, 9 am – 1 pm
Location: N3 Building, classroom 2027 on Thursdays and N1B building, classroom 1715 on Fridays
Oral presentations by the participants are foreseen for Thursday January 11, 9am – 1pm (exact duration depends on the number of participants)