The overall purpose of the course is that the student should be well acquainted with basic concepts, theory, models, and solution methods in time series analysis, models for "dependent" data, especially ARMA-models. Such data are common in economical (e.g., the price development of a product) and in natural science (e.g., meteorological observations) applications. Further, statistical problems of identification, validation, and forecasting for selected ARMA-model and observed data are studied and as well as some generalizations for non-stationary models, like ARIMA-models. Kalman-filters, multivariate time-series, financial ARCH-models are also considered. The part of the course is some methods and techniques for statistical analysis of spatially "dependent" data, such as methods to measure spatial dependency and techniques for spatial interpolating, especially kriging. All methods are illustrated by real data examples in the corresponding Matlab/R programs. An obligatory laboration is part of the course
Time Series Analysis and Spatial Statistics, 7.5 hp
Spring Term 2018
Lectures begin on week starting 15 January 2018
Lectures end during the week of 19 March 2018
English (upon request)
Type of studies
The course requires 90 ECTS including courses in Mathematical Statistics, minimum 12 ECTS, or courses in Statistics, minimum 75 ECTS and in both cases a course in Basic Calculus, 7,5 ECTS. Proficiency in English equivalent to Swedish upper secondary course English A/5. Where the language of instruction is Swedish, applicants must prove proficiency in Swedish to the level required for basic eligibility for higher studies.
Applicants in some programs at Umeå University have guaranteed admission to this course. The number of places for a single course may therefore be limited.
Application deadline was
16 October 2017.
Please note: This second application round is intended only for EU/EEA/Swiss citizens.