Statistical Analysis of Non-numerical Information

Bachelor 2026/2027

ID 1142662

Type: Compulsory course (Economics and Statistics)

Delivered by: Department of Statistics and Data Analysis

Where: Faculty of Economic Sciences

When: 2 year, 3 module

Open to: students of one campus

Language: English

ECTS credits: 4

Contact hours: 40

Full Syllabus Ask Question

Abstract

Categorial Data Analysis is a course for the second year bachelor’s programme students who selected specialization Economics and Statistics. The course covers methods for analyzing qualitative variables, that often receive little attention in the traditional statistics curriculum, but play an important role in statistical practice due to the ubiquity of categorical data, especially in the social sciences. The course consists of two parts, including traditional (non modes) methods for analyzing the relationship between categorical variables and loglinear models. The first section provides basic terminology and notation; describes methods for testing the hypothesis of the independence of two categorical variables, including follow-up components extracting that improve the description of the relationship; covers different measures of association and their probabilistic interpretation. The second section considers loglinear models that allow to characterize the nature of the relationship between variables, determine how the expected cell frequencies of the contingency table depend on the levels of categorical variables and on the interactions between them. The course materials assume that students are familiar with the basic concepts and methods of Calculus, Probability Theory and Mathematical Statistics courses from the 1st and 2nd years of the bachelor’s programme

Learning Objectives

To provide students with a scientific understanding of statistical methods for studying random phenomena in economics
To introduce methods for the quantitative analysis of categorical and other non-numerical statistical data
To develop students' ability to formulate statistical hypotheses and to interpret the results of statistical analyses in a meaningful way
To foster probabilistic and statistical thinking that is essential for successful research and analytical work in modern socio-economic and management-related fields

Expected Learning Outcomes

Explain the fundamental concepts and terminology of categorical data analysis
Construct and analyze contingency tables of various dimensions
Select appropriate statistical methods for analyzing categorical data depending on the research design and data structure
Test hypotheses of independence between categorical variables using asymptotic and exact statistical methods
Quantify the strength of association between categorical variables using appropriate measures of association and interpret their values
Interpret the results of statistical analyses in the context of real-world economic and social science applications
Formulate and estimate loglinear models for two-way and three-way contingency tables
Perform categorical data analysis using Microsoft Excel and statistical software

Course Contents

Introduction to Categorical Data Analysis
Testing Independence in Contingency Tables
o Measures of Association
o Introduction to Loglinear Models
o Two-Way Loglinear Models
Three-Way Loglinear Models

Assessment Elements

Homework 1
Analysis of the association between two dichotomous variables using a 2 × 2 contingency table
Homework 2
Analysis of the association between two categorical variables using an (r x s) contingency table
Homework 3
Homework 4
Three-way loglinear analysis
Class Participation
Assessed on the basis of students' performance on quizzes administered during lectures and seminar sessions
Final Exam
A written exam covering the material studied throughout the course

Interim Assessment

2026/2027 3rd module
0.1 * Homework 2 + 0.1 * Homework 3 + 0.1 * Homework 1 + 0.1 * Class Participation + 0.5 * Final Exam + 0.1 * Homework 4

Bibliography

Recommended Core Bibliography

Ark, L. A. van der, Croon, M. A., & Sijtsma, K. (2005). New Developments in Categorical Data Analysis for the Social and Behavioral Sciences. Mahwah, N.J.: Psychology Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=125950
Upton, G. J. G. (2016). Categorical Data Analysis by Example. Hoboken, New Jersey: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1402878

Recommended Additional Bibliography

Agresti, A. (2013). Categorical Data Analysis (Vol. Third edition). Hoboken, NJ: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=769330
Sutradhar, B. C. (2014). Longitudinal Categorical Data Analysis. New York: Springer. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=881131

Authors

Rychkova Ella Nikolaevna
Astafeva Ekaterina Viktorovna

Course Syllabus