Course detail

Data-Driven Engineering

FSI-RIDAcad. year: 2027/2028

The course introduces students to methods of applied statistics and design of experiments used to solve technical and engineering problems. Emphasis is placed on the statistical evaluation of measurement results, the formulation and testing of hypotheses, modelling relationships between variables, and efficient experimental design.

Students will learn to distinguish between random and systematic variability, quantify the uncertainty of statistical conclusions, and use statistical methods to identify significant factors affecting the technical characteristics under investigation.

Theoretical knowledge is applied throughout the course to examples from engineering practice using statistical software. The course includes an individual semester project focused on the statistical analysis of engineering data, experimental design, or the evaluation of results from experimental measurements or numerical simulations.

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Learning outcomes of the course unit

Upon completion of the course, students will be able to:

  1. Describe and analyse variability in experimental and operational data and distinguish between common and assignable causes of variation.
  2. Use basic probability models to analyse engineering data.
  3. Construct and interpret confidence intervals and perform statistical hypothesis testing.
  4. Assess the suitability of selected statistical methods and verify their underlying assumptions.
  5. Develop and interpret regression models describing relationships between engineering variables.
  6. Design and analyse factorial experiments, including full and fractional factorial designs.
  7. Use design of experiments methods to identify significant factors and optimise engineering processes.
  8. Independently address a more complex engineering problem using statistical software and present the results in a technical report.

Entry knowledge

Basic knowledge of probability and statistics, particularly descriptive statistics, random variables and their distributions. Basic computer skills for working with data are assumed.

Knowledge of advanced statistical methods and experience with specialised statistical software are not required.

Rules for evaluation and completion of the course

The course is completed by obtaining a graded course credit.

Requirements for obtaining the graded course credit:

  • Active participation in computer practicals.
  • Completion and submission of a semester project.
  • A satisfactory assessment of the project, with a brief defence of the methods and results where required.
  • Successful completion of a final assessment of knowledge and skills.

The final assessment of knowledge and skills forms part of the graded course credit and assesses knowledge of basic statistical principles, the ability to select appropriate methods, and the correct interpretation of statistical conclusions. It consists of a written/computer-based component and, where applicable, an oral component.

The final grade is based on the semester project and the final assessment of knowledge and skills. To pass the course, students must meet the minimum requirements for both components.

Aims

The aim of the course is to teach students to independently apply basic statistical methods to the analysis of engineering data and the design of experiments.

Particular emphasis is placed on the ability to correctly formulate a statistical problem, select an appropriate method for solving it, assess whether its assumptions are met, and interpret the results in the context of the engineering problem being addressed.

An integral part of the course is the development of skills in designing efficient experiments, evaluating the effects of individual factors, and drawing conclusions relevant to engineering practice on the basis of statistical analysis.

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

ANDĚL, J. Statistické metody. Praha: MATFYZPRESS, 2003 (CS)
MELLOUN, M. a MILITKÝ, J. Statistické zpracování experimentálních dat. Praha: PLUS, 1994 (CS)
MONTGOMERY, D. C. a RUNGER, G. C. Applied Statistics and Probability for Engineers. Wiley. (EN)
MONTGOMERY, D. C. Design and Analysis of Experiments. Wiley. (EN)

Recommended reading

BOX, G. E. P., HUNTER, J. S. a HUNTER, W. G. Statistics for Experimenters: Design, Innovation, and Discovery. Wiley. (EN)
HAHN, G. J. a SHAPIRO, S. S. Statistical Models in Engineering. Wiley. (CS)

Classification of course in study plans

  • Programme N-IMB-P Master's

    specialization IME , 2 year of study, winter semester, compulsory-optional
    specialization BIO , 2 year of study, winter semester, compulsory-optional

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

Syllabus

  1. Data collection and description; common and assignable causes of variation. Statistical populations and samples.
  2. Probability distributions used in engineering practice. The normal distribution and the sampling distribution of the arithmetic mean.
  3. Statistical assessment of process stability. Basic principles of control charts and assumptions for their use.
  4. Point and interval estimation of parameters. Confidence intervals and their interpretation.
  5. Statistical hypothesis testing I. Principles of hypothesis testing, decision errors, and one-sample tests.
  6. Statistical hypothesis testing II. Comparison of samples, parametric tests and their assumptions.
  7. Correlation analysis. Quantification and interpretation of relationships between variables.
  8. The linear regression model. Parameter estimation, statistical significance, and model diagnostics.
  9. Introduction to design of experiments. Factors, responses, randomisation, replication, and principles of experimental design.
  10. Factorial experiments. Main effects, interactions, and orthogonal experimental designs.
  11. Full and fractional factorial experiments. Selection of an experimental design and evaluation of effects.
  12. Response surface methods. Modelling nonlinear relationships and designing experiments.
  13. Optimisation using designed experiments. Interpretation of results and recommendations for optimal settings.

Computer-assisted exercise

13 hours, compulsory

Teacher / Lecturer

Syllabus

  1. Introduction to statistical software. Data import and basic data analysis.
  2. Probability distributions, the sampling distribution of the mean, and simulation of random sampling.
  3. Analysis of process stability using control charts.
  4. Construction and interpretation of confidence intervals.
  5. One-sample statistical tests.
  6. Two-sample and paired statistical tests.
  7. Correlation analysis and graphical assessment of relationships between variables.
  8. The linear regression model and regression diagnostics.
  9. Design of a simple experiment and identification of experimental factors.
  10. Analysis of a factorial experiment, main effects, and interactions.
  11. Design and analysis of full and fractional factorial experiments.
  12. Response surface modelling.
  13. Response optimisation, interpretation and presentation of experimental results.