(in Polish) Statystyka i eksploracyjna analiza danych 2400-M1ABSEA

The aim of the course is to familiarize students with the fundamentals of statistical analysis to a degree sufficient for independently and effectively analyzing structured data, and interpreting and drawing conclusions from such analyses. The course consists of the following thematic blocks:

BLOCK 1. Introduction to Statistics:
- the importance of statistics and data analysis in business,
- types of data structures, sources of secondary data, construction of primary data, data quality,
- types of variables,
- the concepts of population and sample, the concept of a random variable, the distribution of a random variable, probability density function, cumulative distribution function,
- measures of central tendency, dispersion, and distribution shape: mean, median, mode, quartiles, deciles, quantiles, percentiles, range, interquartile range, variance, standard deviation, coefficient of variation, skewness, kurtosis,
- characteristics of selected statistical distributions: normal distribution, Student's t-distribution, F-distribution, Poisson distribution, Gamma distribution, Beta distribution,
- measures of dependence and association: Pearson, Spearman, and Kendall correlation, Cramér's V coefficient,
- methods of data visualization,
- outliers, box plot, IQR, Z-score, modified Z-score,
- variable transformations: categorization of continuous variables, one-hot encoding, normalization, standardization, winsorization,
- the importance and objectives of data visualization,
- good and bad practices in visualization,
- types of charts relative to data type (continuous, categorical, time series).

BLOCK 2. Statistical Hypothesis Testing:
- hypotheses, test statistics, critical values, p-value, significance level, Type I and Type II errors,
- test power, power and sample size.
- selected statistical tests for one group: normality tests, t-test, Z-test, binomial test, χ² test for one group,
- selected statistical tests for two or more independent groups: t-test, Wilcoxon test, χ² test, Fisher's test. ANOVA, Kruskal-Wallis test, χ² test. Tests for two or more dependent groups: t-test, Wilcoxon test, McNemar's test. ANOVA, Cochran's Q test.

BLOCK 3. Introduction to Econometric Modeling:
- introduction to the linear regression model: line, plane, regression hyperplane, random disturbance, simple versus multiple regression, estimation of the linear regression model, Ordinary Least Squares (OLS) method, residuals, the Gauss-Markov theorem, properties of the OLS estimator,
- the Classical Linear Regression Model (CLRM): CLRM assumptions, interpretation of parameters in the regression model, partial elasticities, testing the statistical significance of parameters, testing the significance of the whole model, testing the significance of selected variables in the model,
- model diagnostics: unusual observations, normality of residuals, collinearity, testing CLRM assumptions,
- extensions of the linear regression model: qualitative explanatory variables, interactions, accounting for nonlinear relationships,
- measures of regression model quality: goodness-of-fit coefficient, information criteria, diagnostic tests, prediction quality.

The course will be delivered in a way that demonstrates the application of various tools for conducting simple statistical analyses, including Microsoft Excel and the programming languages Stata, R, and Python. Prior familiarity with them is not required.

Estimated student workload: 4 ECTS x 25h = 100h
(K) - contact hours (S) - independent work hours
classes: 30h (K) 0h (S)
consultations: 10h (K) 0h (S)
exam: 0h (K) 0h (S)
preparation for classes: 0h (K) 30h (S)
preparation for the credit/pass assessment: 0h (K) 30h (S)
Total: 40h (K) + 60h (S) = 100h

Term 2025Z:

1. Organizational matters; Introduction to Statistics
● Overview of the course syllabus, assessment rules, and recommended literature.
● The importance of statistics and data analysis in business.
● Types of data structures.
● Concepts of population and sample, random variable, probability distribution, probability density function, and cumulative distribution function.
● Selected statistical distributions: normal, Student's t, Snedecor's F, Poisson, Gamma, and Beta distributions.

2. Introduction to the Python programming language
● Loading data from various sources.
● Selecting observations and variables, filtering, sorting.
● Overview of core Python libraries: numpy, pandas, statsmodels.
● Data cleaning, detecting and removing duplicates, handling and imputing missing values.
● Data structure transformations, merging datasets.

3. Measures of central tendency, dispersion, and distribution shape
● Mean, median, mode, quartiles, deciles, quantiles, percentiles.
Range, interquartile range, variance, standard deviation, coefficient of variation.
Skewness and kurtosis.

4. Measures of dependence and association
● Pearson, Spearman, and Kendall correlation coefficients, Cramér’s V.

5. Data visualization
● Outliers: boxplot, outlier detection, IQR, Z-score, modified Z-score.
● Variable transformations: binning of continuous variables, one-hot encoding, normalization, standardization, winsorization.
● Purpose and importance of data visualization.
● Good and bad practices in visualization.
● Types of charts and their suitability for different data types (continuous, categorical, time series).
● Overview of Python visualization libraries: matplotlib, seaborn, plotly, and pandas plotting tools.

6. Hypothesis testing
● Hypotheses, test statistics, critical values, p-value, significance level, Type I and Type II errors.
● Test power, relationship between power and sample size.

7. Selected statistical tests
● Tests for a single group: normality tests, t-test, Z-test, binomial test, chi-square test for a single group.
● Tests for two or more independent groups: t-test, Wilcoxon test, chi-square test, Fisher’s exact test, ANOVA, Kruskal-Wallis test, chi-square test.
● Tests for two or more dependent groups: paired t-test, Wilcoxon signed-rank test, McNemar’s test, repeated measures ANOVA, Cochran’s Q test.

Course coordinators

Term 2025Z:

Maciej Świtała
Ewa Weychert

Term 2026Z:

Maciej Świtała

Type of course

obligatory courses

Learning outcomes

Upon completing the course, the student:

Knowledge:
- knows and understands basic statistical concepts,
- knows and understands the characteristics of selected statistical distributions,
- knows and understands the tools used for conducting statistical inference.

Skills:
- is able to load, clean, and prepare data for analysis,
- is able to draw conclusions based on measures of central tendency, dispersion, and distribution shape, as well as measures of dependence and association,
- is able to visualize data clearly and comprehensibly, and to draw conclusions from such visualizations,
- is able to conduct and interpret statistical tests,
- is able to construct a simple linear regression model and interpret the results obtained.

Competencies:
- is prepared to interpret the results obtained in the course of statistical analyses, based on familiarity with the most important statistical methods and good practices in their use,
- demonstrates the ability to critically analyze the results obtained, based on having discussed examples of the application of these methods during classes.

Assessment criteria

Passing the course requires meeting all three of the following conditions jointly:
1. obtaining at least half of the points for the submitted home project outline;
2. obtaining at least half of the points for the home project;
3. obtaining at least half of the points for the defense of the home project.

The final grade is a weighted average of the above elements: the outline grade (weight 10%), the project grade (30%), and the project defense grade (60%).

Grading scale:
[0%-50%) - fail (ndst)
[50%-60%) - satisfactory (dst)
[60%-70%) - satisfactory plus (dst+)
[70%-80%) - good (db)
[80%-90%) - good plus (db+)
[90%-100%] - very good (bdb)

Bibliography

Downey, A. B. (2014). Think stats: Exploratory data analysis in Python (Version 2.0.27).
Knaflic, C. N. (2015). Storytelling with data: A data visualization guide for business professionals. John Wiley \& Sons, Inc.
Maksimowicz-Ajchel, A. (2007). Wstęp do statystyki. Wydawnictwo Uniwersytetu Warszawskiego.
Mangiafico, S. S. (2015). An R companion for the Handbook of Biological Statistics (Version 1.3.9, revised 2023) [Online handbook]. Rutgers Cooperative Extension. Retrieved from https://rcompanion.org/handbook.
Molin, S. (2021). Hands-on data analysis with pandas: Efficiently perform data collection, wrangling, analysis, and visualization using Python (2nd ed.). Packt Publishing.
Mycielski, J. (2010). Ekonometria. Wydawnictwo Uniwersytetu Warszawskiego.
Pant, D., \& Mukhiya, S. K. (2025). Statistics for Data Scientists and Analysts: Statistical approach to data‑driven decision making using Python. BPB Publications.
Sobczyk, M. (2007). Statystyka. Wydawnictwo Naukowe PWN.
Wooldridge, J. M. (2013). Introductory econometrics. A modern approach. 5th ed. South-Western Cengage Learning.

Term 2025Z:

4. Measures of dependence and association
● Pearson, Spearman, and Kendall correlation coefficients, Cramér’s V.

6. Hypothesis testing
● Hypotheses, test statistics, critical values, p-value, significance level, Type I and Type II errors.
● Test power, relationship between power and sample size.