Research seminar in Statistics
Description
Based on a growing number of data streams and modern experimental devices, more and more collected data shows a functional structure, where each observation corresponds to a curve. Examples range from, e.g., yield curves in econometrics, over infra red absorption spectra in chemometrics to fields like economics, metereology or engineering, where variables of interest are observed continuously over time for each observational unit. Instead of interpreting discrete measurements of these curves as separate variables, it is often beneficial to explicitly incorporate their special functional character into the analysis of this kind of data.
Course Outline
This term the seminar focus on "Functional Data Analysis". In the seminar, state of the art methods are presented suited to handling functional data, including exploratory techniques, regression, and other generalizations of methods well known for scalar data.
Literature
For introductory literature we refer to the respective chapters of the following books:
- Ramsay, J.O. & Silverman, B.W. (2005): "Functional Data Analysis", 2nd Edition, New York: Springer.
- Ramsay, J.O. & Silverman, B.W. (2002): "Applied Functional Data Analysis", New York: Springer.
- Ramsay, J.O., Hooker, G. & Graves, S. (2009): "Functional Data Analysis with R and Matlab", Dordrecht (u.a.): Springer.
- Ferraty, F. & Vieu, P. (2006): "Nonparametric Functional Data Analysis", New York: Springer.
- Cuevas, A. (2014): "A partial overview of the theory of statistics with functional data", Journal of Statistical Planning and Inference, 147, p. 1-23