Lectures:
Defining the problem of multivariate data analysis.
Methods of data analysis: mathematical statistics and exploratory data analysis. The input data types of formal and semantic aspects. Filtration,
missing data, dichotomize, categorization
Preprocessing, transformation. Normalization and standardization. Principal components.
Cluster analysis, non-hierarchical methods, hierarchical methods, presentation and interpretation of results.
Finding associations, automatic creation of hypotheses, presentation and interpretation of results.
Decision tree construction, presentation and interpretation.
Exercise:
Practice methods of lectures on examples of specific data.
Papers on new methods of data mining.
Reports on the results of an analysis.
Projects:
Analysis of specific data from their own experience or from a database.
Preprocessing, selection of appropriate methods.
Own calculations, interpretation.
Presentation of results, documentation.
Computer Labs:
A system for data analysis, control methods, presentation of results, applications.