Courses - Overview
The contents of the chair's courses are listed below. The exact dates of the individual courses can be found in the electronic course catalogue KU.Campus. If you have any questions, please contact the secretary's office.
All important information and materials (exercise sheets, lecture notes, slides, etc.) for the current courses as well as useful links can be found in the e-learning system "ILIAS", section Statistics. All you have to do is log in to KU.Campus with your computer centre ID and register for the desired course.
Bachelor Courses
Summer terms
Descriptive Statistics and Probability Theory - mandatory
Course Number | 82-021-QM03-H-507
Degree | Bachelor
Semester | Summer
Course Type | Lecture and exercise
Participation limit | None
Course Category | Mandatory for the Bachelor program in Business Administration
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
- Students in the field of business administration acquire the basic statistical methods and notions.
- The methodical skills are acquired within the scope of the lecture. Firstly, the statistical theory is taught in order to provide a solid methodical basis.
- Students apply techniques in probability theory and descriptive statistics on practical issues within the scope of the exercises.
- The self-centered working techniques enable students to develop the competence to handle statistical methods self-reliantly as well as to efficiently apply those methods in practice.
Course Content
- Introduction
- Descriptive statistics (incl. indices und measures of concentration and inequality)
- Probability theory
- Introduction (incl. axiom system, conditional probability and Bayes’s theorem)
- Discrete univariate distributions
- Continuous univariate distributions
- Discrete multivariate distributions
- Continuous multivariate distributions
- Limit theorems (incl. Chebyshev's Inequality and Laws of Large Numbers)
Teaching Methods
- Lecture and exercise
Grading
- Final exam (100 %)
Assessment criteria in detail
- Written exam at the end of semester
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
28 h = Time of attendance tutorial
28 h = Preparation and postprocessing tutorial
38 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
Readings
- Küsters, Ulrich (2015): Statistik, Foliensatz, KUE/WFI, Ingolstadt.
- Bamberg, G., Baur, F. und Krapp, M. (2012): Statistik. 17. Auflage, Oldenbourg
- Bamberg, G., Baur, F. und Krapp, M. (2012): Statistik-Arbeitsbuch: Übungsaufgaben-Fallstudien-Lösungen. 9. Auflage, Oldenbourg
- Schira, Josef (2012): Statistische Methoden der VWL und BWL. 4. Auflage, Pearson Studium, München.
- Fahrmeir, L., Künstler, R., Pigeot, I. und Tutz, G. (2011): Statistik - Der Weg zur Datenanalyse.
7. Auflage, Springer-Verlag, Berlin. - Mosler, K. und Schmid, F. (2009): Beschreibende Statistik und Wirtschaftsstatistik. 4. Auflage, Springer-Verlag, Heidelberg.
- Mosler, K. und Schmid, F. (2011): Wahrscheinlichkeitsrechnung und schließende Statistik.
4. Auflage, Springer-Verlag, Heidelberg.
Proseminar Statistics & Econometrics - optional (not SS 2021 and SS 2022)
Course Number | 82-021-PS20-H-0507
Degree | Bachelor
Semester | Summer
Course Type | Proseminar
Participation limit | None
Course Category | Compulsory elective (Bachelor program in Business administration, interdisciplinary master in Mathematics with focus on Business Mathematics)
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
- Students acquire knowledge about the basics of scientific work and the basic approach to conduct statistic and econometric analyses during the contact hours.
- Students acquire expertise within the field of appropriate data handling and are enabled to graphically display, evaluate and present economically relevant data.
- The seminar assignment enables students to acquire knowledge and working methods independently in order to produce a proseminar paper fulfilling the common criteria of scientific writing.
- Students acquire communication and critical faculty skills by presenting, defending and discussing their proseminar papers.
Course Content
- The proseminar deals with the statistical or econometric analysis of empirical data. Therefore students can choose one topic out of an annual changing catalogue. Possible topics will be presented and assigned in a kick-off meeting. Students also have the opportunity to propose own topics. The following aspects are addressed in the class:
- basics of scientific work
- data collection
- data preparation
- data modelling
- building of graphics
- interpretation of statistical or econometric models
- critical reflection of relevant statistical and econometric indicators, methods, models, etc
Teaching Methods
- Weekly class to convey the central course content.
- Creating an academic proseminar paper.
- Presentation and defence of the work at the end of course.
Grading
- Proseminar paper (70 %)
- Presentation (30 %)
Assessment criteria in detail
Because of the competence orientation of this course the proseminar paper and defense of the paper by presentation are mandatory assessment criteria.
- Proseminar paper: On the basis of the written paper it will be assessed whether the student is able to process a given question in a scientific manner.
- Presentation: Presentation to the seminar group to assess the student’s ability of presenting his/her results in a predefined time frame.
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
94 h = Proseminar paper and presentation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
- Descriptive Statistics and Probability Theory (Statistic I)
- Statistical Inference and Multivariate Statistics (Statistic II)
- Computational Statistics with R
Readings
- Will be announced individually in the kick-off meeting.
Computational Statistics with R
The block course takes place for 6 hours each on Fridays and Saturdays at the beginning of the summer terms.
The exact dates will be announced in the KU Campus system.
Lecturer: Philipp Reinhard
Course Number | 82-021-IFM08-H-0507
Degree | Bachelor
Semester | Summer, Winter
Course Type | Integrated Lecture and Exercise
Contact Hours | 2 SWS
Participation limit | 19*
Course Category | Compulsory elective (Bachelor in Business Administration, interdisciplinary master in Mathematics with focus on Business Mathematics), course can be attended by Master students
Number of Credits | 5 ECTS
Language | English or German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and/or Assistants
Learning Outcomes
- Students acquire both baseline information and knowledge of selected programming techniques by using the statistical software environment R.
- The statistical analysis of data using R enables students to appropriately treat, prepare and graphically display empirical data.
- By addressing problems in the broad field of business and economics (i.e. statistical hypothesis testing, linear regression etc.), students gain decision making skills enabling them to conduct an analysis using R in a self-directed and aim-oriented manner.
Course Content
- Basics
- Objects and data structures in R und how to manage them
- Vectors
- Matrizes
- Arrays
- Lists
- Data Frames
- Logic and missing values
- Constructs for program control
- Conditional statements (if … else and the like)
- Loops
- Character strings
- Objects and data structures in R und how to manage them
- Data input and output
- Working with Excel-Data
- Read and write R objects
- Details of the R language
- Functions
- S3-class objects
- Lazy Evaluation
- Graphics with R
- Statistics mit R
- Basic functions
- Random numbers
- Distributions and samples
- Linear models
Teaching Methods
- Integrated Lecture and Exercise
- Programming projects
Grading
- Final exam (100 %)
Assessment criteria in detail
- Final exam: assessment of theoretical and technical aspects of the programming language respectively of the statistical topics covered in class.
Average Workload
28 h = Time of attendance
28 h = Preparation and post-processing
66 h = Homework assignment/ Programming project
28 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
Readings
- Ligges, U. (2008): Programmieren mit R, 3. Auflage, Springer.
- Matloff, N. (2011): The Art of R Programming, No Starch Press.
- Lafaye de Micheaux, P., Drouilhet, R., Liquet, B. (2013): The R software: fundamentals of programming and statistical analysis, Springer
- Venables, W. N., Ripley, B. D. (2002): Modern Applied Statistics with S. 4. Auflage, Springer.
- Rizzo, M.L. (2008): Statistical Computing with R, Chapman Hall.
*Limit due to capacity restriction in computer pools (special admission procedure).
Winter terms
Statistical Inference and Multivariate Statistics - mandatory
Course Number | 82-021-QM04-H-0507
Degree | Bachelor
Semester | Winter
Course Type | Lecture and exercise
Participation limit | None
Course Category | Mandatory (Bachelor in Business Administration)
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
- Students studying business administration acquire the common notions and techniques related to inductive and multivariate statistics within the scope of the courses.
- Students develop the methodical expertise during lecture time. These competencies are also based on the preceding course descriptive statistics and probability theory. The initial lectures introduce the essential theoretical knowledge base in order to broaden the methodical expertise of the students.
- Within the scope of the exercises, students apply techniques in inductive and multivariate statistics on simple issues in the field of business sciences.
- The self-centered working methods enable students to develop the competence enabling them to self-reliantly handle statistical techniques and to efficiently apply those methods in practice.
Course Content
- Statistical Inference
- Sample functions
- Point estimation
- Confidence intervals
- Testing statistical hypotheses
- Multivariate statistics
- Correlation
- Regression analysis
- One-way analysis of variance
- Partial correlation
- Relationships between categorical data
- Relationships between ordinal data
Teaching Methods
- Lecture
- Exercise
Grading
- Final exam 100 %
Assessment criteria in detail
- Written exam at the end of semester
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
28 h = Time of attendance tutorial
28 h = Preparation and postprocessing tutorial
38 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
- Descriptive Statistics and Probability Theory
Readings
- Küsters, Ulrich (2015): Foliensatz Statistik, KUE/WFI, Ingolstadt.
- Bamberg, G., Baur, F. und Krapp, M. (2012): Statistik. 17. Auflage, Oldenbourg
- Bamberg, G., Baur, F. und Krapp, M. (2012): Statistik-Arbeitsbuch: Übungsaufgaben-Fallstudien-Lösungen. 9. Auflage, Oldenbourg
- Schira, Josef (2012): Statistische Methoden der VWL und BWL. 4. Auflage, Pearson Studium, München.
- Fahrmeir, L., Künstler, R., Pigeot, I. and Tutz, G. (2010): Statistik - Der Weg zur Datenanalyse.
7. Auflage, Springer-Verlag, Berlin. - Mosler, K., Schmid, F. (2009): Beschreibende Statistik und Wirtschaftsstatistik. 4. Auflage, Springer-Verlag, Heidelberg.
- Mosler, K., Schmid, F. (2011): Wahrscheinlichkeitsrechnung und schließende Statistik. 4. Auflage, Springer-Verlag, Heidelberg.
Applied Statistical Methods - optional (not WS 2021/2022)
Module Number | 82-021-SCM16-H-0507
Degree | Bachelor
Semester | Winter
Course Type | Lecture/Exercise
Participation Limit | 19*
Creditable for | Compulsory elective
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
- Students acquire the common techniques in the field of descriptive statistics as well as data analysis and regression.
- Using the statistical software environment R allows students to develop the necessary skills enabling them to apply the methods taught on empirical data.
- They develop the personal competence to apply their new theoretical background knowledge on issues in the broad field of business administration and economics in a goal-oriented way.
Module Content
- Overview
- Introduction to the statistical software environment R
- Basics of the language
- Data preparation, graphics and model estimation
- Univariate Statistics including density estimation
- Linear models, especially
- Regression Analysis including residual and multi-collinearity diagnostic
- Variance- and Covariance Analysis
- Regression Models with binary, ordinal and nominal scaled data (incl. log-linear models)
- Nonlinear Regression Models
- Further statistical methods such as:
- Cluster Analysis
- Discriminant Analysis
- Factor Analysis
Teaching Methods
- Lecture
- Excercise
- Substantial reading assignments
- Homework assignments
- Term paper
Grading
- Final exam (50 - 100 %)
- and/or homework assignments (0 – 50 %)
- and/or term paper (0 – 50 %)
The actual grading details are stated at the beginning of the respective semester.
Assessment criteria in detail
Because of the competence orientation of this module it is mandatory to combine a written exam with programming homework assignments or a term paper.
- Written exam: assessment of theoretical aspects of the statistical topics covered in class.
- Homework assignments: assessment of the practical implementation of the topics covered in class by means of a programming language such as R.
- Term paper: assessment of capability to illustrate a given problem in a context that is broader compared to other assessment alternatives.
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
28 h = Time of attendance tutorial
28 h = Preparation and postprocessing tutorial
19 h = Homework assignment/ Term paper
19 h = Exam preparation
150 h = Total workload
Previous Knowledge/Prerequisites
- Mathematics for Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
- Computational Statistics with R
Readings
- Venables, W. N., Ripley, B. D. (2002): Modern Applied Statistics with S. 4te Auflage, Springer.
- Venables, W. N., Ripley, B. D. (2000): S-Programming. Springer.
- Ligges, U. (2008): Programmieren mit R. 3te Auflage, Springer.
- Matloff, N. (2011): The Art of R Programming, No Starch Press.
- Wright, D.B., London, K. (2009): Modern Regression Techniques Using R, Sage.
- Küsters, U., Kalinowski C. (2001): Traditionelle Verfahren der multivariaten Statistik, in: Hippner H., Küsters, U., Meyer, M. und Wilde, K.W. (eds.): Handbuch Data Mining im Marketing: Knowledge Discovery in Marketing Databases. Braunschweig/Wiesbaden, pp. 131 – 192.
- Chatterjee, S., Price, B. (1995): Praxis der Regressionsanalyse. Oldenbourg Verlag.
*Limit due to capacity restriction in computer pools.
Computational Statistics with R
The block course takes place for 6 hours each on Fridays and Saturdays at the beginning of the winter terms.
The exact dates will be announced in the KU Campus system.
Lecturer: Philipp Reinhard
Course Number | 82-021-IFM08-H-0507
Degree | Bachelor
Semester | Summer, Winter
Course Type | Integrated Lecture and Exercise
Contact Hours | 2 SWS
Participation limit | 19*
Course Category | Compulsory elective (Bachelor in Business Administration, interdisciplinary master in Mathematics with focus on Business Mathematics), course can be attended by Master students
Number of Credits | 5 ECTS
Language | English or German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and/or Assistants
Learning Outcomes
- Students acquire both baseline information and knowledge of selected programming techniques by using the statistical software environment R.
- The statistical analysis of data using R enables students to appropriately treat, prepare and graphically display empirical data.
- By addressing problems in the broad field of business and economics (i.e. statistical hypothesis testing, linear regression etc.), students gain decision making skills enabling them to conduct an analysis using R in a self-directed and aim-oriented manner.
Course Content
- Basics
- Objects and data structures in R und how to manage them
- Vectors
- Matrizes
- Arrays
- Lists
- Data Frames
- Logic and missing values
- Constructs for program control
- Conditional statements (if … else and the like)
- Loops
- Character strings
- Objects and data structures in R und how to manage them
- Data input and output
- Working with Excel-Data
- Read and write R objects
- Details of the R language
- Functions
- S3-class objects
- Lazy Evaluation
- Graphics with R
- Statistics mit R
- Basic functions
- Random numbers
- Distributions and samples
- Linear models
Teaching Methods
- Integrated Lecture and Exercise
- Programming projects
Grading
- Final exam (100 %)
Assessment criteria in detail
- Final exam: assessment of theoretical and technical aspects of the programming language respectively of the statistical topics covered in class.
Average Workload
28 h = Time of attendance
28 h = Preparation and post-processing
66 h = Homework assignment/ Programming project
28 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
Readings
- Ligges, U. (2008): Programmieren mit R, 3. Auflage, Springer.
- Matloff, N. (2011): The Art of R Programming, No Starch Press.
- Lafaye de Micheaux, P., Drouilhet, R., Liquet, B. (2013): The R software: fundamentals of programming and statistical analysis, Springer
- Venables, W. N., Ripley, B. D. (2002): Modern Applied Statistics with S. 4. Auflage, Springer.
- Rizzo, M.L. (2008): Statistical Computing with R, Chapman Hall.
*Limit due to capacity restriction in computer pools (special admission procedure).
.
Master courses
Summer terms
Time Series Analysis - elective BA&OR/FACT/MARKT
Course Number |88-021-OM01-H-0408
Degree | Master
Semester | Summer
Course Type | Lecture and Exercise
Participation limit | 19*
Course Category | Compulsory elective (Business Analytics & OR, FACT, MARKT, Master flex. Sociology – Focus “Methods of social empirical research”, interdisciplinary master in Mathematics with focus on Business Mathematics), Mandatory (“lehramtsgeeigneter” Master in Mathematics - Economics, “Lehramt” with a combination of Mathematics – Economics)
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
- Students develop the methodical expertise and theoretical knowledge base to name and explain practically relevant statistical techniques in the field of time series.
- Students can apply and calculate selected techniques using the statistical software environment R as well as interpret the respective results.
- By learning the fundamental conceptional and theoretical extensions of time series techniques, for example in the field of capital market theory and marketing, students develop the necessary skills to decide in a problem-centered way related to the context.
Course Content
- ARIMA(p,d,q)-Models in detail (Box-Jenkins-Methodology)
- Models
- Estimation
- Unit-Root-Tests (determination of d)
- Model identification (determination of p and q)
- Model evaluation and residual diagnostics
- Forecasting formulas and confidence intervals
- Overview about Seasonal ARIMA models
- Overview about ARIMA-based regression models
- Intervention analysis
- Transfer functions
- Outlier detection
- Overview about ARCH and GARCH models
Teaching Methods
- Lecture and Reading
Grading
- Final exam (100%)
Assessment criteria in detail
- Written exam at the end of semester
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
28 h = Time of attendance tutorial
28 h = Preparation and postprocessing tutorial
38 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
- Applied Statistics
- Business Forecasting
Readings
- Küsters, U. (2015): Zeitreihenanalyse: Box-Jenkins-Modelle. KUE.
- Cryer, J.D. und Chan, K.-S. (2008): Time Series Analysis: With Applications in R. Springer.
- Wei, W.W.S. (2006): Time Series Analysis: Univariate and Multivariate Methods. 2te Auflage. Addison-Wesley.
- Diebold, F.X. (2007): Elements of Forecasting. 4te Auflage. Thomson-South Western.
*Limit due to capacity restriction in computer pools.
Seminar Statistics - elective FACT - compulsory elective BA&OR/MARKT (not SS 2022)
Module Number | 88-021-OM07-H-0408
Degree | Master
Semester | Winter or summer
Course Type | Seminar
Participation limit | None
Creditable for | Compulsory elective (Business Analytics & OR, MARKT, Master flex. Sociology – Focus “Methods of social empirical research”, interdisciplinary master in Mathematics with focus on Business administration)
Contact Hours | 2 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
-
- Students learn to solve a practical case by applying statistical methods to data analytical problems. The main focus is on the methodological issues.
- Within the scope of the preparation of their seminar papers, students can collect, select and critically assess relevant literature. Additionally, students can design and create a seminar paper considering standards of scientific work.
- Discussing the seminar topics in a small group setting broadens the participants’ social skills and their capacity for teamwork. Students develop communication skills and an ability to take criticism within the scope of presenting, defending and discussing their seminar papers.
Module Content
-
- Writing a paper about a forecasting problem related to managerial practice (in consultation with the lecturer alternative topics are possible).
- The paper’s topic can either be chosen by the student with (data possibly to be collected by the student) or proposed by the lecturer.
- The case studies can be carried out individually or in teams of two.
Teaching Methods
-
- Seminar
Grading
-
- Writing a paper (case study and solution) (60%)
- Presenting the paper (problem and results) (20%)
- Designing a poster (20%)
Assessment criteria in detail
Because of the competence orientation of this module the proseminar paper and defense of the paper by presentation are mandatory assessment criteria.
- Paper: assessment of the ability to process a given question in a scientific manner.
- Presentation: assessment of the ability to present and defend a scientific subject in a predefined time frame.
- Poster: assessment of the ability to illustrate the fundamental results of the seminar paper in limited space.
Average Workload
28 h = Time of attendance lecture
22 h = Preparation and postprocessing lecture
100 h = Proseminar paper and presentation
150 h = Total workload
Previous Knowledge
-
- Mathematics for Business
- Descriptive Statistics and Probability Theorie
- Statistical Inference and Multivariate Statistics
- Business Forecasting
Readings
-
- Will be announced in the kick-off meeting.
Data Science Concepts - Lecture course (not SS 2021 and SS 2022)
Course Number | xx
Degree | Master
Semester | Summer
Course Type | Lecture and Reading
Participation limit | 19*
Course Category | Compulsory elective (Business Analytics & OR)
Contact Hours | 2 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods & BA and Business Informatics
Lecturer | Prof. Dr. Ulrich Küsters and Prof. Thomas Setzer
Learning Outcomes
- Students can summarize and interpret scientific publications and books and are able to derive implications from that.
- Students develop cognitive skills in order to independently acquire new knowledge and new working techniques in the field of theory and the application of practice-relevant methods of machine learning, to work towards results in a goal-oriented manner and to discuss these in a well-founded way. Thereby, they critically question what they read and are able to connect it with their prior knowledge and design new solutions and applications.
Course Content
- Overview of Data Science Methods and Basic Procedures of Statistical Learning
- Data space and data geometric basics of Statistical Learning
- Bias-Variance Trade-off and Error Decomposition
- Methods of supervised learning and feature assessment
- Models for dimension reduction or feature reduction
- Outlook
Teaching Methods
- Reading assignments
- Class discussion
- If possible, participants should take a charged laptop with pre-installed software with them to the events. The software to be installed will be announced soon.
Grading
- Written exam or oral examination (100%)
Assessment criteria in detail
- Final exam at the end of semester
Average Workload
28 h = Time of attendance lecture
72 h = Reading
50 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics für Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
- Basic knowledge of statistical programming software such as R or Python is recommended. Participation in the course Data Science Tools is ideal, but not mandatory.
Readings
Will be announced in the kick off meeting
Data Science Methods (not SS 2022)
Course Number | 88-021-QM05
Degree | Master
Semester | Summer or Winter
Course Type | Lecture and Exercise
Participation limit | 19*
Course Category | Compulsory elective (Business Analytics)
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods & BA and Business Informatics
Lecturer | Prof. Dr. Ulrich Küsters and Prof. Dr. Thomas Setzer
Learning Outcomes
- The students possess the methodical competence and the theoretical basis and can thus name and explain important statistical methods of data science relevant to practice.
- Students can apply and compute selected methods with the help of a statistical software environment such as R or Python and interpret their results.
- By means of the important conceptual and theoretical extensions of the methods of data science, students acquire the competences to make problem-oriented and context-related decisions.
Course Content
- Overview of Data Science Methods and Basic Procedures of Machine Learning
- Data rooms and data geometric basics of machine learning
- Bias-Variance Trade-off and Error Decomposition
- Methods of supervised learning and feature assessment
- Models for dimension reduction or feature reduction
- Outlook
Teaching Methods
- Lecture and Exercise
- If possible, participants should take a charged laptop with pre-installed software with them to the events. The software to be installed will be announced.
Grading
- Final exam (100%)
Assessment criteria in detail
- Written exam at the end of semester
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
28 h = Time of attendance tutorial
28 h = Preparation and postprocessing tutorial
38 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics for Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
- Basic knowledge of statistical programming software such as R or Python is recommended. Participation in the course Data Science Tools is ideal, but not mandatory.
Readings
Will be announced in the kick off meeting
Winter terms
Business Forecasting - mandatory BA&OR- compulsory elective FACT/MARKT
Course Number | 88-021-MG04-H-0408
Degree | Master
Semester | Winter
Course Type | Lecture and Exercise
Participation limit | _
Course Category | Mandatory (Business Analytics & OR, „Lehramtsgeeigneter“ Master in Mathematics - Economics, „Lehramt“ with a combination of Mathematics – Economics)
Compulsory elective (FACT, MARKT, Master flex. Sociology – Focus “Methods of social empirical research”, interdisciplinary master in Mathematics with focus on Business administration)
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistic and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
- Students understand the most important forecasting techniques and their related software implementation, which are required in the broad field of business administration, particularly in marketing, in logistics and in the production.
- Within the scope of exercises, students learn how to apply the common forecasting techniques on practical issues in sales forecasts and inventory holding using a statistical programming environment such as R.
- This course puts students into the position to grasp the theory behind forecasting models and to apply them in practice.
- Students are enabled to critically reflect the issued forecasts.
Course Content
- Lecture:
- Overview
- Forecast evaluation
- Naïve forecasting methods
- Exponential smoothing
- Basics of the Box-Jenkins Methodology (ARIMA Models)
- Dynamic regression models
- Miscellanea
- Exercise:
- Introduction to the statistical software environment
- Case study naïve forecasting methods
- Case study exponential smoothing
- Case study Box-Jenkins models
- Case study dynamic regression models
- Case study forecasting intermittent demand
Teaching Methods
-
- Lecture
- Exercise
Grading
-
- Final exam 100%
Assessment criteria in detail
-
- Written exam at the end of semester
Average Workload
28 h = Time of attendance lecture
28 h = Preparation and postprocessing lecture
28 h = Time of attendance tutorial
28 h = Preparation and postprocessing tutorial
38 h = Exam preparation
150 h = Total workload
Previous Knowledge
-
- Mathematics for Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
Readings
- Küsters, U. (2015): Statistische Prognoseverfahren für Betriebswirte (Foliensatz). KUE/WFI.
- Ligges, U. (2008): Programmieren mit R. 3. Auflage, Springer.
- Makridakis S., Wheelwright, S. C. und Hyndman, R. J. (1998): Forecasting, Methods and Applications. 3te Auflage. Wiley.
- Hyndmann R.J., Athanasopoulos G. (2014): Forecasting, Principles and Practice, otexts
- Mertens, P. und Rässler, S. (Hrsg. 2012): Prognoserechnung. Siebte, wesentlich überarbeitete und erweiterte Auflage. Physica-Verlag, Heidelberg.
Data Science Tools - compulsory elective (BA & OR)
Module Number | XXX
Degree | Master
Semester | Winter
Course Type | Lecture and Tutorial
Participation Limit | 19*
Creditable for | Compulsory elective (BA & OR)
Contact Hours | 4 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
-
- Students understand the conceptual, methodological and the IT-theoretical foundations of Data Science, apply this knowledge to process, and analyze data sets using statistical software environments like R and development environments like RStudio.
- By applying selected techniques, students broaden their methodical skills.
- Based on example data sets, students analyze, evaluate, and solve business problems by applying appropriate Data Science tools and methods.
- Students understand how to construct basic queries in relational databases like mySQL using basic SQL commands as well as SQL interfaces to a statistic system.
- This course uses a script as well as various textbooks, articles, software manuals and elaborated examples. Therefore, students learn how to collect, select, and use information to create functional solutions.
Module Content
-
- Overview
- Data Science: Scope and Tools
- Workflow model
- Description of selected small and medium sized data sets to illustrate the application of tools and methods
- Basics of the statistical software environments, the interactive development environment and the relational data base management system
- Data visualization
- Basic elements of graphics
- Grammar of graphics
- Aesthetics
- Scales
- Facets
- Layers
- Themes
- Basic statistical Graphics
- Univariate Graphics
- Bivariate Graphics
- Multivariate Graphics
- Maps
- Data handling
- Data Structures
- Reading data
- Selecting, filtering and arranging data
- Tidying up data
- Joining data
- Functional programming for automation and iteration
- Databases and SQL
- Interfaces
- Save data sets in SQL
- Process data in SQL
- Selected methods of statistical learning
- Basic statistical tools
- Sampling
- Random numbers
- Bootstrap
- Model evaluation
- Cross validation
- Confusion tables
- Evaluation measures
- ROC: Receiver Operator Characteristics
- Supervised learning
- K Nearest Neighbor (KNN)
- Classification trees
- Unsupervised learning
- Hierarchical clustering
- K-Means
- Dimension reduction using the singular value decomposition
- Outlook
Teaching Methods
-
- Reading assignments
- Lecture
- Tutorial
- Participants should bring a charged laptop with an installed version of R and RStudio.
Grading
-
- Written exam (100 %)
Assessment criteria in detail
- Final exam at the end of semester
Workload (in hours)
42 h = Preparation Lecture
28 h = Time of attendance lecture
28 h = Time of attendance tutorial
28 h = Preparation and post-processing tutorial
24 h = Exam preparation
150 h = Total workload
Previous Knowledge
-
- Mathematics for Students of Economics Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
- Programming skills (preferably in R or in a matrix- and/or object- oriented language)
Literature
Primary literature
- Baumer, B.S, Kaplan, D.T. und Horton, N.J. (2017): Modern Data Science with R. CRC Press.
Secondary literature
- Wickham, H. und Grolemund, G. (2016): R for Data Science - Import, tidy, transform, visualize, and model data. O’Reilly
Will be announced in the kick-off meeting.
*Limit due to capacity restriction in computer pools.
Data Science Theory (Lecture Course) (not WS 2021/2022)
Course Number | xx
Degree | Master and PhD
Semester | Winter
Course Type | Lecture and Reading
Participation limit | 19*
Course Category | Compulsory elective (Business Analytics & OR) and WFI-PhD-Program
Contact Hours | 2 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters
Learning Outcomes
- Students learn the mathematical basics of selected methods of machine and statistical learning.
- Upon successful completion of the module, students can independently classify, interpret and derive implications of scientific work in machine and statistical learning in the different methodological areas of machine and statistical learning.
- Students develop skills in order to independently acquire new knowledge and new working techniques in the field of theoretically based statistical and machine learning approaches, to work towards results in a goal-oriented manner and to discuss these in a well-founded way.
Course Content
- Overview of the theoretical foundations of Data Science and Statistical Learning
- Algorithms and inference
- Frequentist versus Bayesian inference
- Maximum Likelihood (ML)
- Generalized Linear Models (GLM) and extensions
- Bootstrap inference and confidence intervals
- Trees, random forests and boosting methods
- Neural networks
- Miscellaneous
Teaching Methods
- Reading assignments
- Class discussion
Grading
- Written exam or oral examination (100%)
Assessment criteria in detail
- Examination at the end of semester
Average Workload
28 h = Time of attendance lecture
72 h = Reading
50 h = Exam preparation
150 h = Total workload
Previous Knowledge
- Mathematics für Business
- Descriptive Statistics and Probability Theory
- Statistical Inference and Multivariate Statistics
- Basic knowledge of statistical programming software such as R or Python is recommended. Participation in the courses Data Science Tools and/or Data Science Concepts is ideal, but not mandatory.
Readings
Will be announced in the kick off meeting
Seminar Statistics - elective FACT - compulsory elective BA&OR/MARKT (not WS 2021/2022)
Module Number | 88-021-OM07-H-0408
Degree | Master
Semester | Winter or summer
Course Type | Seminar
Participation limit | None
Creditable for | Compulsory elective (Business Analytics & OR, MARKT, Master flex. Sociology – Focus “Methods of social empirical research”, interdisciplinary master in Mathematics with focus on Business administration)
Contact Hours | 2 SWS
Number of Credits | 5 ECTS
Language | German
Chair | Statistics and Quantitative Methods
Lecturer | Prof. Dr. Ulrich Küsters and Assistants
Learning Outcomes
-
- Students learn to solve a practical case by applying statistical methods to data analytical problems. The main focus is on the methodological issues.
- Within the scope of the preparation of their seminar papers, students can collect, select and critically assess relevant literature. Additionally, students can design and create a seminar paper considering standards of scientific work.
- Discussing the seminar topics in a small group setting broadens the participants’ social skills and their capacity for teamwork. Students develop communication skills and an ability to take criticism within the scope of presenting, defending and discussing their seminar papers.
Module Content
-
- Writing a paper about a forecasting problem related to managerial practice (in consultation with the lecturer alternative topics are possible).
- The paper’s topic can either be chosen by the student with (data possibly to be collected by the student) or proposed by the lecturer.
- The case studies can be carried out individually or in teams of two.
Teaching Methods
-
- Seminar
Grading
-
- Writing a paper (case study and solution) (60%)
- Presenting the paper (problem and results) (20%)
- Designing a poster (20%)
Assessment criteria in detail
Because of the competence orientation of this module the proseminar paper and defense of the paper by presentation are mandatory assessment criteria.
- Paper: assessment of the ability to process a given question in a scientific manner.
- Presentation: assessment of the ability to present and defend a scientific subject in a predefined time frame.
- Poster: assessment of the ability to illustrate the fundamental results of the seminar paper in limited space.
Average Workload
28 h = Time of attendance lecture
22 h = Preparation and postprocessing lecture
100 h = Proseminar paper and presentation
150 h = Total workload
Previous Knowledge
-
- Mathematics for Business
- Descriptive Statistics and Probability Theorie
- Statistical Inference and Multivariate Statistics
- Business Forecasting
Readings
-
- Will be announced in the kick-off meeting.