The course is focused on time series analysis of geological data (e.g., stratigraphic data, downhole well logs, etc. ) and proxy for paleo-climatic data. The non-parametric methods of singular spectrum analysis will be introduced to the students and used to recognize trends, periodic forcing, background noise from data and forecasting. The approach of the course is practical and will make large use of the R data analysis software (https://www.r-project.org/about.html). Students should come to class with a personal computer and the R software installed to be able to follow the examples shown in the class and exercises.

In this short course we will:

·  Introduce time series analysis.

·  Learn the basic usage of R

·  Understand Singular Spectrum Analysis

·  Use SSA to solve practical problems

None

·  The student must demonstrate the ability to master the basic knowledge of the methods used to describe and analyze the data series studied during the course.

·  The student must demonstrate the understanding of the concepts and theories provided by the course; be able to independently acquire and analyze the types of time series data described during the course; be able to assess the significance of the results obtained from their analysis.

·  The student must demonstrate the possession of the ability to use knowledge and concepts learned according to the specific logic of the discipline. He must be able to identify the most appropriate analysis techniques for specific contexts and to envisage hypotheses of analysis of non-trivial cases.

·  The student must show that he is able to communicate his knowledge, ideas and possible problems, in a clear way and using language properties.

The student is encouraged to study and learn independently using the recommended texts and to ask specific questions in the face of possible problems

The teaching material prepared by the lecturer in addition to recommended textbooks (such as for instance slides, lecture notes, exercises, bibliography) and communications from the lecturer specific to the course can be found inside the Moodle platform › blended.uniurb.it

Course books

J.B. Elsner and A.A. Tsonis (1996). Singular Spectrum Analysis, A New Tool in Time Series Analysis. Springer Science+Business Media, LLC

Golyandina, N.; V. Nekrutkin, and A. Zhigljavsky (2001). Analysis of Time Series Structure: SSA and related techniques. Hapman&Hall/CRC, New York - London.