Course code MateD005

Credit points 2

Multivariate Data Analysis I

Total Hours in Course80

Number of hours for lectures16

Number of hours for seminars and practical classes16

Independent study hours48

Date of course confirmation04.09.2019

Responsible UnitDepartment of Control Systems

Course developers

author Vadības sistēmu katedra

Līga Paura

Dr. agr.

author Vadības sistēmu katedra

Irina Arhipova

Dr. sc. ing.

Course abstract

PhD student acquire multivariate data analyses methods, as also check the model assumptions violations. The study course is oriented to multivariate methods choice acquisition and methods comparison. During the studies the real examples related to biology, agriculture and other sciences are using. Statistical software is provides for problem tasks solving. The course topics are the following: parametric and non-parametric two and more sample statistical methods, ANOVA, repeated measures ANOVA, GLM.

Learning outcomes and their assessment

After completing the course Ph.D. student will have:
• knowledge about multivariate data analysis methods for emerging scientific theories and its application for PhD research on professional fields (during the practical classes the necessary statistical methods for testing the hypothesis of the doctoral thesis are analyzed);
• skills individually evaluate and select multivariate data analysis methods for scientific researches of important, original and international cited researches (during the practical classes the necessary statistical methods for the data analysis of the doctoral thesis have been selected);
• competences in collaboration with PhD supervisor individually perform critical analysis and evaluation. Solve important scientific or innovative tasks and individually propose research ideas (independent work has been developed and defended).

Course Content(Calendar)

1. Introduction to study course.
2. Statistical analysis software.
3. Statistical hypothesys testing. Types of hypothesys testing. Types of errors.
4. Parametric methods for data analysis. Testing of Assumptions
5. Non-parametric methods for data analysis and aplication in research.
6. Parametric methods for two independent and dependent samples.
7. Non-parametric methods for two independent samples.
8. Parametric methods for two dependent samples.
9. Parametric methods for three and more samples.
10. One-way, two-way and multy-way analysis of variance (ANOVA).
11. Testing ANOVA assumptions.
12. Multiple comparison analysis testing in ANOVA.
13. Non-parametric methods for three and more samples.
14. Repeated Measures ANOVA.
15. Introduction to Generalized Linear Models.
16. Defending of independent work.

Requirements for awarding credit points

Independent work have been developed and defended. Oral defense of a project at the end of the course. At least three different statistical methods for the real data analysis should be used.

Description of the organization and tasks of students’ independent work

The organization of independent work during the semester is independently studying literature, using academic staff member consultations.

Criteria for Evaluating Learning Outcomes

The assessment of learning outcomes depends on the degree of development of the independent work. To obtain the minimal assessment it is necessary to formulate and test the hypotheses using at least 3 statistical methods, based on the data of the doctoral thesis: two and more samples parametric or non-parametric statistical methods, ANOVA, repeated measures ANOVA or GLM.

Compulsory reading

1. Are Hugo Pripp. (2013) Statistics in food science and nutrition. New York : Springer, 66 pp.
2. François Chollet & J.J. Allaire (2018) Deep learning with R. Shelter Island, NY: Manning Publications Co., 335 pp.
3. James Gareth, at al. (2017) An introduction to statistical learning: with applications in R. New York : Springer, 426 pp.
4. Joseph F. Hair, Jr., William C. Black, Barry J. Babin, Rolph E. Anderson (2014) Multivariate data analysis. Harlow, Essex: Pearson, 734 pp.
5. Robert I. Kabacoff (2015) R in action: data analysis and graphics with R. Shelter Island, NY: Manning, 579 pp.
6. Siegmund Brandt. (2014) Data analysis: statistical and computational methods for scientists and engineer. Springer, 523 pp.

Further reading

1. John H. Schuenemeyer, Lawrence J. Drew. (2011). Statistics for Earth and Environmental Scientists. Hoboken, New Jersey: John Wiley & Sons, 407 pp.
2. Joseph F. Hair [et al.] (2010) Multivariate data analysis: a global perspective. Upper Saddle River [etc.]: Pearson, 800 pp.
3. Klaus Backhaus, Bernd Erichson, Wulff Plinke, Rolf Weiber (2000) Multivariate Analysemethoden: eine anwendungsorientierte Einführung. Berlin etc.: Springer, 661 pp.
4. Massimiliano Bonamente. (2013) Statistics and analysis of scientific data. New York: Springer, 301 pp.
5. Nathabandu T. Kottegoda, Renzo Rosso (2008) Applied statistics for civil and environmental engineers. Oxford; Malden, MA: Blackwell Publishing, 718 pp.

Periodicals and other sources

1. Statistical Analysis and Data Mining.Hoboken, Wiley-Blackwell. ISSN:1932-1864. E-ISSN:1932-1872
2. Electronic Journal of Applied Statistical Analysis. ESE - Salento University Publishing. ISSN:2070-5948


Elective course for all LLU doctoral programs.