Multivariate Techniques: Statistical Analysis and Case Studies

General

• Code: 276-190612
• Semester: 6th
• Study Level: Undergraduate
• Course type: Επιλογής, Ειδικού υποβάθρου
• Teaching and exams language: Greek
• Teaching Methods (Hours/Week): Lectures (2)
• ECTS Units: 3
• Course homepage: https://moodle.teithe.gr/course/view.php?id=2539
• Instructors: Petridis Dimitrios

Course Contents

The need to jointly investigate the relationship of a large number of variables measured on a specific substrate such as water volume, mass of a food, water volume, mass of a food habitat of organisms, led to the invention of special techniques known as multivariate analyses. These techniques are frequently and thoroughly applied to chemical, mechanical, organoleptic and other qualitative characteristics of processed food products, and are manipulated exclusively via statistical software. The contribution of these techniques dramatically advances the results of research and adds to the high satisfaction and scientific merit of the leader of the survey.

Summary of contents

• Introduction to multidimensionality.
• Multiple regression and correlation analysis. Diagnostic validity criteria of the proposed model.
• Logistic regression: Binomial, Ordinal, Multinomial, Poisson. Diagnostic validity criteria of the methods.
• Principal Components Analysis (PCA).
• Factor Analysis.
• Cluster Analysis.
• Multivariate analysis of variance (MANOVA).
• Multiple Discriminant Analysis (MDA).
• Classification and regression trees.
• Canonical Correlation.
• Redundancy Analysis.
• Reciprocal Averaging).
• Canonical Correspondence Analysis.
• Selection of the most appropriate experimental designs and application of specific statistical analyses with popular programs (MINITAB, JMP).

Educational Goals

• Acquiring knowledge in specialized statistical methods related to the integrated profile of a product.
• The understanding and interpretation of the physicochemical and organoleptic parameters that characterize the general properties of food or group of foods in terms of their structure.
• The ability to statistically describe and evaluate the contribution rate of each parameter in the structural composition of the product.
• The skill to organize experimental conditions for the synthesis of a product, to change and improve structural properties and to capture in detail the overall image of the product.
• The acquisition of substantial experience in the application of statistical techniques to the degree of utilization of food quality.

General Skills

• Searching, analyzing, interpreting and synthesizing data and information, using the necessary technologies.
• Adjusting in new situations.
• Decision making.
• Autonomous work.
• Group work.
• Working in an interdisciplinary environment.
• Developing new research ideas.
• Promoting free thinking.

Teaching Methods

Face to face:

• Lectures (theory and problems) in the classroom.
• Practical exercises (practice in the statistical software MINITAB by processing data from the food industry).

Use of ICT means

• Presentation with PowerPoint slides using PC and projector.
• Posting course material and communicating with students on the Moodle online platform.
• Use of electronic devices for recording and statistical processing of data.

Teaching Organization

Students Evaluation

Written final exams including:

• Multiple choice questions.
• Critical thinking questions.
• Problems based on data from the. food industry using the statistical software MINITAB.

Recommended Bibliography

1. Agresti A. (1996). An Introduction to Categorical Data Analysis. John Wiley and Sons, New York, 372 p.
2. Belsley D.A., Kuh E. and Welsch R.E. (1980). Regression Diagnostics. John Wiley & Sons, N. Jersey 310 p.
3. Bowman A. W. and Azzalini A. (1997). Applied smoothing techniques for data analysis. Clarendon Press, Oxford. 193 p.
4. Breiman L., Friedman J.H., Olshen R.A. and Stone C.J. (1984). Classification and regression trees.  Wadsworth & Brooks/Cole Advanced Books & Software., Monterey, 354 p.
5. Collett D. (2003). Modelling Binary Data, 2nd ed. Chapman & Hall, London, 344 p.
6. Gorsuch R. L. (1983). Factor Analysis, 2nd ed. Hillsdale, Lawrence Erlbaum Associates, New Jersey, 425 p.
7. Greenacre M.J. (2007). Correspondence Analysis in Practice. 2nd ed., Academic Press, London, 296 p.Gower J.C. and Hand D.J. (1996). Biplots. Chapman and Hall, London, 277 p.
8. Lance G.N. and Williams W.T. (1967). A general theory of classification sorting strategies. I. hierarchical systems. Computer Journal, 9, 373-380.
9. McLachlan J.B. (2005). Discriminant analysis and strategical pattern recognition. John Wiley and Sons, N. Jersey, 544 p.
10. Montgomery D.C., Peck E.A. and Vining G.G. (2012). Introduction to Linear Regression Analysis. 5th ed. John Wiley & Sons, N. Jersey, 672 p.
11. Ter Braak C.J.F. (1986). Canonical correspondence analysis: a new eigenvector technique for multivariate direct gradient analysis. Ecology, 67, 1167-1179.
12. Warton D.I. and Hudson H.M.2004. A MANOVA statistic is just as powerful as distance-based statistics, for multivariate abundances. Ecology, 85, 858-874.
13. Velicer, W. F. and Jackson, D. (1990). Component analysis vs factor analysis: some issues in selecting an appropriate procedure. Multivariate Behavioral Research, 25, 1-28.

Related Research Journals

1. Journal of Multivariate Analysis.
2. Ecotoxicology and Environmental Safety.
3. Desalination and Water Treatment.
4. Journal of Food Science.