PhD Programme: Gdansk University of Technology, Faculty of Management and Economics (2017)




The aims of this lecture are as follows: [1] To present selected methods of quantitative data analysis for business and economics; [2] To provide students with decision-making capabilities based on the quantitative analyses; [3] To improve students’ use of econometric and statistical packages;


Mathematics, statistics, microeconomics, macroeconomics.

Suggested Textbooks

Maddala, G. S. (1977), Econometrics, McGraw-Hill, New York.

Charemza, W. W. and Deadman, D. F. (1992), New Directions in Econometric Practice, Edward Elgar

Software: Gretl

download for Windows useres
download for Mac useres

Course Outline

Block 1.: What links your data to probability?

Describing the data set: averages and deviation from averages;

Outlier detection: finding and dealing with abnormalities;

Activity: arithmetic average, geometric average, weighted average, median, standard deviation, skewness, kurtosis, histogram, counting rules, outlier detection;

Exercises: probability, expected value, and descriptive statistics;

Data (Gretl): excess kurtosis: Euro/PLN, 1993-2017;

Data (Gretl): asymetry: R&D and unemployment;

Lecture: box-and-whisker graph, outlier detection;

Example (Excel): outlier analysis;

Block 2: Adding precision to your observations: hypothesis testing

Testing: calculating probability of similarity;

Presenting the results: tables and visualisations;

Activity: sampling distribution, tests for two (and more) means, tests for proportions, tests for variances, testing for independence

Data and Exercises (Gretl): hypothesis testing;

Exercises: hypothesis testing: ANOVA;

Examples (Gretl): testing examples;

Examples (Gretl): hypothesis testing: components of HDI;

Handout: chapter on hypothesis testing (not ready);

Block 3: Expected and unexpected reactions: regression analysis

Activity: estimation: coefficients, elasticities; residual diagnostics: normality of residuals, heteroscedasticity, expected value of residuals; goodness-of-fit: R^2, adjusted R^2, log-likelihood, information criteria, model selection

Exercises: constant term, slope, and elasticity;

Data and Exercises (Gretl): OLS in GRETL;

Data for Exercises: Dr. Plama and his car;

Handout: chapter on OLS regression;

Block 4: Stacking-up observations: introduction to panel analysis

Activity: pooled models; fixed and random effect models; marginal effects; diagnostics: normality of residuals, heteroscedasticity, expected value of residuals; goodness-of-fit: R^2, adjusted R^2, log-likelihood; information criteria

Lecture: PowerPoint presentation;

Exercises (Gretl): fixed and random effects;

Data (Gretl): R&D and economic activity;

Block 5: Tracing out changes in time

Spurious correlation: when trends affect the results (and what to do with it);

Causality: predictive power and (econometric) causality;

Prediction: forecasting again, impulse-response analysis;

Activity: stationary and non-stationary time series; testing for unit root; detrending; Granger causality; multivariate time series models: impulse-response, variance decomposition

Exercises: Spurious correlation and trends;

Data: Highly seasonal data on tourism in Poland;

Data (Gretl): Inflation in Central Europe;

Lecture: PowerPoint presentation;

Exercises: Granger causality; stability;

Exercises: impulse-response;