Multivariate Data Analysis
- Credits: 10
- Ending: Examination
- Range: 16sP
- Semester: winter
- Faculty of Economic Informatics
Teachers
Included in study programs
Teaching results
This course is designed to provide an overview of an interesting, new and fast-growing area of multivariate data analysis. Individual multivariate statistical methods do not form closed circuits, but are constantly enriched with new approaches with multivariate solutions and the possibility of their application in practice.
After completing the course, students will acquire:
Knowledge:
- acquire knowledge of the latest findings in the field of multivariate statistical methods,
- by working on the course project, students will use this knowledge in solving practical tasks using any statistical program package;
Skills:
- develop an understanding of the main principles of multivariate data analysis,
- develop your ability to identify an appropriate multivariate statistical method and to evaluate its use in addressing real economic and social challenges in practice;
Competencies:
- will be able to formulate, solve and present the results of applied research;
- improved writing and presentation skills.
Indicative content
This course is intended to supplement other courses of statistical data analysis, which are based on the analysis of a set of diverse features, the number of which sometimes reaches several tens. In these cases, the traditional one-dimensional approach to the solution is very difficult, often impracticable. The solution to this problem in statistics is addressed by a set of procedures and methods, which is called multivariate analysis.
Support literature
R. S. (2021). Segmentation Analytics with SAS® Viya®: An Approach to Clustering and Visualization. Cary, North Carolina: SAS Institute Inc. ISBN 978-1-951684-06-8
2. Hair, J. F. - Black, W. C. - Babin, B. J. - Anderson, R. E. (2010). Multivariate data analysis. 7th ed. New York: Macmillan Publishing Company. ISBN 13: 978-0138132637
3. Kattamuri, Sarma, S. (2017). Predictive Modeling with SAS® Enterprise miner™. North Carolina : SAS Institute Inc. ISBN 978-1-62960-264-6
4. Khattree, R. – Naik, N. D. (200). Multivariate data reduction and discrimination with SAS® Software. Cary, North Carolina: SAS Institute Inc. ISBN 1-58025-696-1
5. Sharma, S. (1996). Applied multivariate techniques. New York: John Wiley & Sons. ISBN 0-471-31064-6
6. Rencher. A. C.. (1995) Methods of Multivariate Analysis. New York: John Willey & Sons. ISBN 0-471-57152-0
7. Tabachnick, B.G. – Fidell, L. S. (2014). Using Multivariate statistics. 6th ed., Edinburg : Pearson Education Limited. ISBN 13: 978-1-292-02131-7
8. Vojtková, M. - Sodomová, E. (2015). Classification of EU countries according to selected indicators from the field of business demography using self-organising maps. In Zeszyty naukowe. - Kraków : Uniwersytet Ekonomiczny w Krakowie. ISSN 1898-6447, no. 11, pp. 37-52.
9. Šoltés, E. - Vojtková, M. - Šoltésová, T. (2020). Changes in the Geographical Distribution of Youth Poverty and Social Exclusion in EU Member Countries Between 2008 and 2017. In Moravian Geographical Reports. Brno : The Czech Academy of Sciences. ISSN 1210-8812, vol. 28, no. 1, pp. 2-15 online.
10. Vojtková, M. - Kotlebová, E. - Sivašová, D. (2019). Determinants Affecting Health of Slovak Population and their Quantification. In Statistika : Statistics and Economy Journal. - Praha : Český statistický úřad, 2019. ISSN 1804-8765, vol. 99, no. 4, pp. 434-450 online.
11. Krasňanská, D. - Komara, S. - Vojtková, M. (2021). Keyword Categorization Using Statistical Methods. In Tem Journal: Technology, Education, Management, Informatics : Journal of the Association for Information Communication Technologies, Education and Science. - Novi Pazar : UIKTEN. ISSN 2217-8333, vol. 10, no. 3, pp. 1377‐1384 online.
Literature will be continuously updated with the latest scientific and professional titles.
Syllabus
The course is delivered in cycles with content aimed at expanding knowledge of: 1. Introduction to multivariate statistical methods. Description of multivariate data. Data preparation. Multivariate data analysis procedure. Classification of multivariate statistical methods. 2. Methods of analysis of hidden relationships: Method of principal components and factor analysis. Mathematical expression of the principal components, their properties, determination of their number and interpretation. Mathematical model of factor analysis, general procedure (estimation methods, factor rotation methods). Comparison of factor analysis and methods of principal components. 3. Methods of interdependency analysis: Cluster analysis. Measures of similarity of objects. Hierarchical and non-hierarchical clustering procedures. Clustering methods. Determination of the number of significant clusters and their interpretation. New trends in clustering./ Multidimensional scaling. / Correspondence analysis. 4. Methods of dependency analysis: Discriminant analysis. Assumptions of using discriminant analysis. Descriptive task of discriminant analysis. Interpretation of discriminant functions. Classification task of discriminant analysis. Verification of classification accuracy./ Logistic Regression. / Multivariate Analysis of Variance. / Conjoint Analysis.
Requirements to complete the course
30 % semester project processed in statistical software or open software environment (e.g. SAS, SPSS, R, Python)
30 % presentation of the semester project
40 % final exam
Student workload
Total study load (in hours): 260 hours
Distribution of study load
Lectures participation: 16 hours
Preparation for lectures: 64 hours
Elaboration of Semester project: 100 hours
Preparation for final exam: 80 hours
Language whose command is required to complete the course
Slovak
Date of approval: 11.03.2024
Date of the latest change: 03.02.2022