Lehrende: Prof. Dr. phil. Stefan Evert
Veranstaltungsart: Proseminar
Orga-Einheit: FB02 / Sprach- und Literaturwissenschaft (Institut)
Anzeige im Stundenplan: Linguistic Theory
Fach:
Anrechenbar für:
Semesterwochenstunden: 2
Unterrichtssprache: Englisch
Min. | Max. Teilnehmerzahl: - | -
Lehrinhalte: In recent years, quantitative evidence – whether in the form of corpus frequencies or experimental data – has become indispensable to linguistic research. A statistical analysis of such data is essential in order to rule out the possibility that observed patterns and effects may just be a coincidence resulting from sampling variation. The main goals of this course are (i) to explain the basic principles of statistical inference and introduce a range of hypothesis tests and other statistical techniques, with a particular focus on the analysis of corpus frequency data, and (ii) to familiarise participants with carrying out statistical analyses on the computer, using the open-source software package R, so that they can immediately apply techniques from the course to their own problems and data sets. NB: This course will be offered as a semi-block course, with regular, open-ended meetings every three weeks on Friday afternoon (not every week as shown in TUCaN). In addition, there will be an extended two-day workshop at the end of the lecture period, in which participants present the results of their practice projects. Further details about the schedules will be discussed in the first meeting (Oct 21st).
Literatur:
Voraussetzungen: The course is open to students from all disciplines, subject to availability of free places. The teaching language will be English or German, depending on preferences of registered participants. Certificate requirements: Regular, active participation in the course. Completion of small homework exercises. Completion and presentation of extended practice project, including a written report.