Course type: compulsory
Lecturer: Gregor Sočan, Ph.D., Assistant Professor
 

For the timeline see Curriculum.

Prerequisites:

• Enrolment into the first year of the programme.

Content (Syllabus outline):
Selected topics from the following list are treated in the course:

• Correspondence analysis.
• Measurement models: An overview of measurement models in social science. Classical test theory: true score and measurement error; reliability and its assessment; the practical use of a reliability coefficient. Introduction to logistic test models: parameter estimation and interpretation; assessment of model fit. Principles of the construction of composite measures.

Objectives and competences:
Students successfully completing this course understand how the method of data collection affects the analyses that are appropriate with categorical data, are able to perform standard testing and estimation tasks involving categorical data, and understand the different multivariate generalizations of independence, including latent variables. They are able to formulate, fit, test and interpret log-linear models with or without dependent variables.
They are able to perform and interpret simple and multiple correspondence analysis. Students are introduced to modern methods of psychometric analysis, applicable to measurement problems in social science, including both classical test theory and item response theory. They are familiar with assumptions, basic procedures, theoretical rationale and limitations of different approaches..

Intended learning outcomes:
Understanding of the fundamental principles of the classical test theory and the item response theory. Knowledge of the measurement models and the item response models. Knowledge of procedures for the reliability and validity assessment and the acceptability criteria.
Familiarity with the most important methods of categorical data analysis and log-linear modeling, with ability to implement these analyses using commercially available statistical software.