Lehrveranstaltungen im SS 18
The topic of this term’s seminar is:
Statistical properties of the cryptocurrency market
Participants are required to write a seminar paper on their chosen topic and give a short presentation by the end of the term. Each participant’s topic will be agreed upon based on adequacy and personal interest. The focus of this seminar is on quantitative analysis which involves computing in statistical software, such as Matlab, R, or Python. Depending on the number of participants, purely literature-based topics might be offered as well.
Students are able to
- select, acquire, and process necessary market data.
- use statistical software, such as Matlab, R, or Python, to analyze market data.
- interpret and discuss results critically, and put them into economically meaningful context.
- write a scientific paper and present its content in a scientific talk.
A.F. Bariviera, M.J. Basgall, W. Hasperué, M. Naiouf. Some stylized facts of the Bitcoin market. Physica A, 484:82-90, 2017.
T. Takaishi. Statistical properties and multifractality of Bitcoin. 2017.
J. Chu, S. Nadarajah, S. Chan. Statistical Analysis of the Exchange Rate of Bitcoin. PLoS ONE, 10(7):1-27, 2015.
P. Katsiampa. Volatility estimation for Bitcoin: A comparison of GARCH models. Economics Letters, 158:3-6, 2017.
A. Eross, F. McGroarty, A. Urquhart, S. Wolfe. The Intraday Dynamics of Bitcoin. 2017.
Methods of Assessment:
Preparation of a seminar paper (20-30 pages) and its presentation (15-20 minutes).
The first meeting (details see above) serves to introduce potential topics. Please register for this meeting by email to marcel.wollschlaeger (at) uni-due.dewith subject "Seminar Selected Topics in RM SS18". Allocation of topics is planned to be completed by April 27, 2018. Please note that deregistration and thus avoiding receiving malus points for not fulfilling the examination requirements is only possible until May 31, 2018.
A basic knowledge of statistical software, such as Matlab, R, or Python, is sufficient. Having taken the course Zeitreihenanalyse is ideal.