IBM SPSS Statistics. Level 5. Multivariate statistical analysis - course RUB 34,990. from Specialist, training 32 ac. h., Date: September 17, 2023.

A professional teacher-practitioner with extensive and varied work experience, as well as more than 10 years of teaching experience. Explains educational material in an engaging, intelligible manner, using many interesting examples from his own practice. The brightness and liveliness of Alina Viktorovna’s presentation helps listeners quickly and fully assimilate the curriculum. The teacher answers in detail all questions that arise from the audience and carefully comments on the situations being analyzed.
Alina Viktorovna has several higher educations in the specialties “Information Technology” and “Economist”. Holds an academic degree of Candidate of Technical Sciences in the field of automation and control of technical processes in industry. Participated in the development of statistical models for the automation of the technological process of sheet glass production, in projects on implementation of statistical methods for process control in the automotive industry (at plants such as AvtoVAZ, KamAZ, GAZ and etc.). Analyzes the healthcare system of the regions of the Russian Federation. Takes part in a project to identify entrepreneurial tendencies among schoolchildren as an analyst.
She has developed many educational and methodological complexes, and has repeatedly taken part in the work of the certification commission for the defense of qualifying works. Author of 17 scientific works, including scientific articles in Russian and foreign publications. Has a certificate from the German company Q-DAS to conduct specialized training on statistical process control for the BOSCH company.
Alina Viktorovna has an impeccable command of methodologies for describing business processes, system modeling, static methods of data processing and IS design standards. In her classes, she gives examples from different work areas so that the material is equally understandable to students from different industries.

Module 1. Cluster analysis and its application (2 ac. h.)

- Multidimensional classification methods
- Concept and areas of application of cluster analysis
- Cluster analysis tasks
- Cluster analysis methods
- Advantages and disadvantages of cluster analysis
- Stages of cluster analysis
- Initial data for cluster analysis
- Measures the distance between objects
- Analysis of classification quality

Module 2. Hierarchical cluster analysis (4 ac. h.)

- Features of hierarchical cluster analysis
- Algorithm of hierarchical methods of cluster analysis
- Measures the distance between clusters
- Procedure Distances
- Measures of difference
- Similarity measures
- Procedure Hierarchical cluster analysis
- Selecting a hierarchical cluster analysis method
- Results of the Hierarchical Cluster Analysis procedure
- Graphical representation of the results of hierarchical cluster analysis
- Setting up statistics for the Hierarchical Cluster Analysis procedure
- Saving new variables

Module 3. Classification using the k-means method (2 ac. h.)

- The essence and features of the k-means method
- Algorithm of the k-means method
- Procedure Cluster analysis using k-means method
- Results of the procedure Cluster analysis using the k-means method
- Setting the number of iterations
- Setting up additional parameters
- Results of displaying additional settings
- Saving new variables
- Graphical presentation of results

Module 4. Two-stage cluster analysis (4 ac. h.)

- Features of two-stage cluster analysis
- Prerequisites for two-stage cluster analysis
- Algorithm for two-stage cluster analysis
- Procedure Two-stage cluster analysis
- Summary of model results
- Assessment of cluster structure
- View information about clusters
- Display information on clusters
- Output control
- Output of the Two-Step Cluster Analysis procedure
- Additional Cluster Viewer panel
- Selection of observations by clusters
- Parameters of the Two-stage cluster analysis procedure

Module 5. Dimensionality reduction methods: factor and component analysis (4 ac. h.)

- The concept of factor analysis
- Purpose and objectives of factor analysis
- Stages of factor analysis
- Prerequisites for the use of factor analysis
- Component analysis algorithm
- Factor analysis algorithm
- Comparison of factor and component analyzes
- Prerequisites for the use of factor and component analyzes
- Procedure Factor analysis
- Results of the Factor Analysis procedure
- Rules for selecting factors
- Selecting a factor analysis method
- Factor rotation problem
- Adjustment of factor rotation
- Parameters of the Factor analysis procedure
- Output of descriptive statistics
- Saving factor values

Module 6. Response-based classification: discriminant analysis (4 ac. h.)

- Segmentation based on responses
- Response-based segmentation methods
- Initial data for discriminant analysis
- Similarities between discriminant analysis and logistic regression
- Differences between discriminant analysis and logistic regression
- Purpose and objectives of discriminant analysis
- Prerequisites for discriminant analysis
- Stages of discriminant analysis
- Methods of discriminant analysis
- Initial data
- Linear discriminant analysis model
- Procedure Discriminant analysis
- Results of the Discriminant Analysis procedure
- Statistics of the Discriminant Analysis procedure
- Method of stepwise selection procedure Discriminant analysis
- Classification based on the results of discriminant analysis
- Classification statistics
- Saving new variables

Module 7. Multivariate analysis of variance (4 ac. h.)

- Multivariate analysis of variance
- Setting parameters for the OLM-multidimensional procedure
- Main results of multivariate analysis of variance
- ANOVA with repeated measures
- GLM procedure - repeated measurements
- Setting parameters for the OLM-repeated measurements procedure

Module 8. Classification models based on decision trees (8 ac. h.)

- The essence of the method of constructing a decision tree
- Areas of application of the decision tree
- Features and prerequisites for using the decision tree method
- Methods for constructing a decision tree
- Comparison of methods for constructing a decision tree
- Procedure Classification Trees
- Interpretation and study of decision trees
- Checking the adequacy of the model
- Customizing the output in the Classification Trees procedure
- Settings and parameters of the Classification Trees procedure
- Rules for classifying observations
- Criteria in the Classification Trees procedure
- Regression decision trees
- Construction of regression decision trees