Statistical Methods II.

The course focuses on enhancing students’ knowledge and skills in data analysis. It follows on from courses covering descriptive and inferential statistics, such as Statistical Methods I.
The aim is to introduce students to selected multivariate statistical methods used to measure attitudes, segment respondents, and reduce datasets. Students will learn how to apply factor analysis, correspondence analysis, and basic clustering techniques in practice. They will also explore how to use survey research to measure preferences and attitudes.
Emphasis is placed on understanding and interpreting results, and on selecting suitable methods for specific analytical tasks. Theoretical explanations are limited to what is necessary for practical application.
Students work with example datasets in R Studio, using basic R packages for analysis and data visualisation.
The course is designed for intermediate users looking to deepen their statistical skills and apply multivariate methods to real-world data.

Applications: http://czv.vsb.cz/kurzy

1. Measuring attitudes and preferences; rating scales
2. Data consistency and design of consistent batteries
3. Normalisation of heterogeneous item batteries
4. Data clustering and respondent segmentation
5. Item description; horizontal and vertical analysis
6. Exploratory factor analysis and latent class identification
7. Correspondence analysis and clustering in contingency tables
8. Clustering methods: hierarchical clustering and K-means
9. Confirmatory factor analysis and model quality assessment
10. Structural equation modelling and causal models
The final two topics will be introduced during practical sessions only. Students
are not required to apply them in their assignments.