Modul (6 Credits)

Advanced R for Econometricians

Name im Diploma Supplement

Advanced R for Econometricians

Verantwortlich

Prof. Dr. Christoph Hanck

Voraus­setzungen

Siehe Prüfungsordnung.

Workload

180 Stunden studentischer Workload gesamt, davon:

• Präsenzzeit: 60 Stunden
• Vorbereitung, Nachbereitung: 60 Stunden
• Prüfungsvorbereitung: 60 Stunden

Dauer

Das Modul erstreckt sich über 1 Semester.

Qualifikations­ziele

Students

• know the strengths and limitations of the high-level statistical programming language R
• thoroughly understand the R ecosystem and have a profound understanding in selected fields of advanced R programming
• can apply their skills in advanced statistical and econometric applications
• are able to document and communicate scientific results in a reproducible manner
• are prepared for implementing big data applications using R

Prüfungs­modalitäten

Weighted average of a (group) R-project (70%) and a presentation (30%, usually about 20 minutes).

Verwendung in Studiengängen

• BWL EaF MasterWahlpflichtbereich 1.-3. FS, Wahlpflicht
• ECMX MasterWahlpflichtbereichME6 Applied Econometrics 1.-3. FS, Wahlpflicht
• VWL MasterWahlpflichtbereich I 1.-3. FS, Wahlpflicht
• WiInf MasterWahlpflichtbereichWahlpflichtbereich II: Informatik, BWL, VWLWahlpflichtmodule der Volkswirtschaftslehre 1.-3. FS, Wahlpflicht

Bestandteile

Vorlesung mit integrierter Übung (6 Credits)

Advanced R for Econometricians

---

Name im Diploma Supplement

Advanced R for Econometricians

Anbieter

Lehrstuhl für Ökonometrie

Lehrperson

Prof. Dr. Christoph Hanck, M.Sc. Martin Christopher Arnold

Turnus

unregelmäßig

SWS

4

Sprache

englisch

maximale Hörerschaft

unbeschränkt

Hörerschaft

vgl. Modul

---

empfohlenes Vorwissen

A solid understanding of basic R programming as, for example, taught in our Master-level econometrics courses is required.

Abstract

This course teaches advanced topics in R programming that become increasingly relevant for everyday applications in both applied and theoretical econometrics and empirical economics.

The first part of the course covers intermediate concepts in functional and object orientated programming, error handling, profiling and benchmarking as well as a treatment of selected R packages tailored for big data applications. Students are also introduced to reporting with dynamic documents. Part II deals with the tidyverse, a collection of packages designed for modern applications in data science. The third part introduces topics such as multi-core computing, C++ integration and other cutting-edge R extensions.

Students are prepared for applications in future studies and are able to efficiently tackle research-related programming tasks.

Lehrinhalte

Part I

• R at its Heart: Functional Programming
• Getting it right: debugging, profiling and testing
• Reporting: Reproducible Research with R Markdown

Part II

• A Grammar of graphics: ggplot2
• Keep it clean: selected tidyverse packages
• Getting data: webscraping and text mining

Part III

• Version control: git and github
• Need for speed: Rcpp and RcppArmadillo
• Harnessing power: parallelization
• Show it to others: Shiny, R Packages

Literaturangaben

• Eddelbuettel, D. (2013). Seamless R and C++ Integration with Rcpp. Springer
• Grolemund, G.; Wickham, H. (2017); R for Data Science. O’Reilly
• Matloff, N. (2011). The Art of R Programming. No Starch Press
• Wickham, H. (2019). Advanced R. CRC Press
• Wickham, H. (2009). ggplot2 - Elegant Graphics for Data Analysis. Springer
• Xie, Y. (2018); R Markdown: The Definitive Guide. CRC Press

didaktisches Konzept

Presentation, discussion and joint solving of programming exercises.

Die Veranstaltung entspricht einem Vorlesungsanteil von 2 SWS und einem Übungsanteil von 2 SWS.