3677 Multivariate Data Analysis , 5 sp
The course is an introduction to multivariate analysis (i.e. statistical techniques that simultaneously analyse multiple measurements on individuals or objects). The course covers techniques such as MANOVA, Principal Component Analysis, Factor Analysis, and Cluster Analysis. The statistical program SPSS is used in the course.
The course is built on the concept of cooperative learning in small teams. You will get a joint grade for the overall performance of your team.
This course is included in the study plan for master's studies in Marketing, Logistics and Management, and can be included as a methods course in master's or doctoral studies in any other subjects than statistics.
Students with Statistics as their minor should take the course Multivariate Data Analysis (8 ECTS, course code 3613) in their bachelor's studies. That course is also recommended for students with a quantitative interest with other subjects as their major.
The two courses are taught together, with a smaller number of lectures (and analyses) for course 3677.
You are familiar with the features of multivariate data, can explain the logic behind multivariate analysis and have a working knowledge of the multivariate techniques.
- examine and prepare data for multivariate analysis;
- apply multivariate methods to well-defined research questions and can carry out multivariate data analysis using SPSS;
- interpret and utilize the analysis results, and present the results in written reports;
- dissect and evaluate research reports were multivariate analysis are applied.
International examples and cases are used, and international articles are reviewed from a statistical perspectiv.
The course is built on the concept of cooperative learning in small mixed student teams (national and international students on BSc, MSC and PhD level).
Who can take this course
The Hanken course 7777 FUM or 7778 Statistisk analys, or similar skills in hypothesis testing, ANOVA and regression analysis recommended
Teaching and timetable
Lectures & computer labs.
Workload and assessment
134 hours divided into
scheduled contact hours: 26 h
non-scheduled work: 108 h
Contact hours: Lectures, exercises & computer labs (26 h).
Self-study: Preparing for the weekly lectures (reading about the concepts covered during the lectures, analysing examples etc), 24 h.
Article reviews (preparation and reporting), 40 h.
Assignment (data analysing and reporting), 24 h.
Final exam (preparation, writing and evaluation), 20 h.
Final exam (open book) 40%
Article reviews 30%
Computer assignments and activity points 30%
Additional individual assignment for doctoral students.
Litteratur och undervisningsmaterial
- Hair, J. F., Black, W.C, Babin, B. J. & Anderson, R. E. (2010). Multivariate data analysis: a global perspective. 7th ed. or earlier. Upper Saddle River (N.J.): Prentice Hall.
Selected chapters as specified by the instructor.
Student who have completed the 8 ECTS version of this course (code 3613) cannot take this 5 ECTS version.
Open university quota: 3
Quota for JOO-students: 3