Monographic lecture: Use of data mining algorithms in psychology: cluster analysis
General data
Course ID: | WF-R-PS-WMAD |
Erasmus code / ISCED: |
14.4
|
Course title: | Monographic lecture: Use of data mining algorithms in psychology: cluster analysis |
Name in Polish: | WM: Wykorzystanie algorytmów data mining w psychologii: analiza skupień |
Organizational unit: | Institute of Psychology |
Course groups: |
(in Polish) Grupa przedmiotów ogólnouczelnianych - Doktoranci (in Polish) Przedmioty dla doktorantów psychologii (in Polish) Wykłady monograficzne kierunkowe z psychologii (in Polish) Wykłady monograficzne pozakierunkowe |
ECTS credit allocation (and other scores): |
(not available)
|
Language: | Polish |
Subject level: | intermediate |
Learning outcome code/codes: | SD_ PS _W02 SD_ PS _W04 SD_ PS _W05 SD_ PS _K04 SD_ PS _K05 |
Short description: |
The aim of the course is to familiarize PhD students with the algorithms carrying out cluster analysis, combining this method with systems of structural equations as well as using it to plot profiles of research participants and test the fit of empirical curves to model curves. |
Full description: |
1. Introduction to Generalized k-means Cluster Analysis algorithms, basic information about the method 2. Basic information on the operation of the algorithm: grouping the subjects into clusters. 3. Basic information on how the algorithm works: calculating differences between clusters. 4. Basic information on the operation of the algorithm: determining the results of people in clusters on the basis of the normalized mean. 5. Conducting a cluster analysis and reporting the results - exercise 1. 6. Conducting a cluster analysis and reporting the results - exercise 2. 7. Conducting a cluster analysis and reporting the results - exercise 3. 8. Basic assumptions of modeling with systems of structural equations 9. Calculation of the first model using the system of structural equations in AMOS. 10. Calculating cluster analysis for variables from the structural model. Determining the characteristics of clusters in terms of variables. 11. Calculation of the second model using the system of structural equations in AMOS. 12. Calculating cluster analysis for variables from the second structural model. Determining the characteristics of clusters in terms of variables. 13. Plotting a theoretical curve. 14. Plotting an empirical curve based on the results of cluster analysis. 15. Estimating the fit of the empirical curve to the theoretical curve. |
Bibliography: |
Elder, J., Hill, T., Miner, G., Nisbet, B., Delen, D., & Fast, A. (2012). Practical Text Mining and Statistical Analysis for Nono-structured Text Data Application. Oxford: Elsevier. Nisbet, R., Elder, J., & Miner, G. (2009). Handbook of statistical analysis and data mining applications. Burlington, MA: Academic Press (Elsevier). Szymańska, A. (2017b). Wykorzystanie analizy skupień metodą data mining do wykreślania profili osób badanych w badaniach psychologicznych [Using cluster analysis in the data mining method to draw profiles of participants surveyed in psychological research]. Studia Psychologiczne, 55(1), 25–40. |
Efekty kształcenia i opis ECTS: |
KNOWLEDGE: - PhD students correctly use the terminology of the cluster analysis method, have knowledge of how to classify objects, normalized mean, etc. SKILLS: - students carry out cluster analysis with the use of algorithms COMPETENCES: - students correctly interpret the results of the analysis Description of ECTS credits Participation in classes: 30 hours Preparation for classes and preparation of reports, reading literature: 30 hours |
Assessment methods and assessment criteria: |
The basis for completing the course is submitting the final report presenting the results prepared using the cluster analysis method |
Copyright by Cardinal Stefan Wyszynski University in Warsaw.