Time Series Analysis and Spatial Statistics, 7.5 credits

Contents

The main purpose of the course is that the student should be well aquainted with the basic notions, theory, models and methods for solutions, in time series analysis and spatial statistics. The course covers models for time dependent or spatially dependent data. Such data frequently occurs  in financial (e.g. the price development of a merchandise) and scientific (e.g. metheorological observations, radar signales) applications.

The course consists of two parts.

Part 1 (6,5 hp) Theory. The part consists of the general theory of time series, stationary and non-stationary models, e.g. ARMA- and ARIMA-models, prediction of time series, spectral theory, parameter estimation, spectrum and filtration. The part also covers methods for measuring spatial dependence (variogram, covariogram), and techniques for spatial interpolation, especially kriging.

Part 2 (1 hp) Lab Assignments. The part consists of analysis of time series and spatial data using suitable software.

Expected learning outcomes

For a passing grade, the student must be able to

Knowledge and understanding

• independently define the notions expectation, covariance function and spectral distribution for time series
• independently define parametric ARMA-type models for the mean
• thoroughly explain how ARMA-models can be expanded to ARIMA-, FARIMA- and ARCH-models
• describe Kalman filtration in general terms
• thoroughly explain how variograms and covariograms are derived
• thoroughly explain how the (spatial) interpolation methods "The inverse distance method" and "Kriging" work

Skills

• identify trends and seasonal variation in time series
• derive and estimate expectation, covariance function and spectral distribution for time series, analyse their connections, and derive the uncertainty of the estimates
• predict the future of observed time series of different lengths, and critically evaluate the results
• apply parametric mean models of ARMA-type, analyse the models' properties and fit real data to them
• interpret spatial dependence using variograma and covariograms
• predict (spatial) data using the interpolation methods "The inverse distance method" and "Kriging", and critically evaluate the results

Judgement and approach

• clearly present the reults from time series analyses and analyses of spatial data, and evaluate the resultats from a scientific perspective

Required Knowledge

The course requires 12 ECTS in Mathematical Statistics and 22,5 ECTS in Calculus including Calculus in several variables and Differential Equations. Proficiency in English equivalent to Swedish upper secondary course English 5/A. Where the language of instruction is Swedish, applicants must prove proficiency in Swedish to the level required for basic eligibility for higher studies.
 

Form of instruction

The teaching mainly consists of lectures and lessons.

Examination modes

Part 1 is examined  by a written exam. Part 2 is examined by written lab reports (U/G).
On part 1, one of the following grades is assigned: Fail (U), Pass (G) or Pass with distinction (VG). On part 2, one of the following grades is assigned: Fail (U) or Pass (G). For the whole course, one of the following grades is assigned: Fail (U), Pass (G) or Pass with distinction (VG). In order to receive a passing grade on the course, all parts must be completed with a passing grade. The course grade is decided by the grade on Part 1, and is assigned only when all mandatory examination has been completed. A student who has received a passing grade on a test is not allowed to retake the test in order to receive a higher grade.

A student who has not received a passing grade after participating in two tests has the right to be assigned another examiner, unless there are certain circumstances prohibiting this (see the Higher Education Ordinance, chapter 6, 22§). A request to be assigned another examiner should be adressed to the head of department for the department of mathematics and mathematical statistics. The possibility of being examined based on the current version of the syllabus is guaranteed for at least two years following the student's first participation in the course.