Lecturer(s)
|
-
Houda Michal, Mgr. Ph.D.
-
Klicnarová Jana, doc. RNDr. Ph.D.
|
Course content
|
Lectures: 1 - Introduction to the course, economical times series and its basic properties, assignments; 2 - Correlation - correlation arrays, correlation coeficients. 3 - Introduction to linear regression, least square method. 4 - Linear regression, different types of dependence, curve fitting. 5 - Linear regression - practical applications, coefficient of determination, normal model, assumptions and applications. 6 - Introduction to Time series models, objectives of TS analysis, errors ,measures of goodness of fit in times series. 7 - classical model of economical times series (trend, seasonality, long-term cycle), decomposition of time series, trend tests. 8 - Seasonality in TS - Small trend method, regression methods. 9 - Periodicity in TS - spectral analysis, periodogram, tests. 10 - Adaptive modelling in TS, using of moving averages. 11 - Exponencial smoothing in times series context. 12 - Randomness tests. Autocorrelation, stationarity. 13 - AR and MA models. 14 - Introduction into Box-Jenkins metodology.
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Dialogic (discussion, interview, brainstorming), Work with multi-media resources (texts, internet, IT technologies), Blended learning
- Class attendance
- 42 hours per semester
- Semestral paper
- 42 hours per semester
- Preparation for credit
- 28 hours per semester
- Preparation for exam
- 28 hours per semester
- Preparation for classes
- 28 hours per semester
|
Learning outcomes
|
The aim of the course is to introduce regression analysis and classical statistical methods for times series analysis - trend, seasonal and cycle adjustment and in short to introduce modern methods of time series analysis - Box-Jenkins methodology.
Students understand the basic principles of regression analysis and times series analysis and are able to apply these method to solution economical problems. Students are able to use software to carry out appropriate analysis.
|
Prerequisites
|
Equivalence: Statistické modelování a analýza časových řad - SMAC, KSMAC
|
Assessment methods and criteria
|
Combined exam, Test
Credit Requirements: To duly submit assignment tasks and to obtain at least 40% of points from credit tests. (Two tests during a semester). Examination Requirements: Exam has two parts - written and oral. In the written part, students have to prove that they can recognise types of optimization problems, to choose suitable methods to solve them and suggest a suitable solution. To pass this part it is necessary to obtain at least 50 percent of points from the test. The written part could be forgiven if the student has at least 65 percent of points from the credit tests. The oral examination is focused on work with PC and discussions about the solution of the written part of the examination. Final mark is based on the results of the credit tests, the written and oral parts of the examination. To pass the oral part it is necessary to answer at least one of the three given questions.
|
Recommended literature
|
-
DRAPER, N., SMITH, H.:. Applied Regression analysis. Wiley and Sons, New York, 1981.
-
HAMILTON, James D. Time series analysis. Princeton: Princeton University Press, xiv, 799 s., 1994. ISBN 06-910-4289-6.
-
Hyndman, Rob J., Athanasopoulos, G. Forecasting: Principles and Practice. OTexts: Melbourne, Australia, 2018. ISBN 978-0-9875071-1-2.
-
MONTGOMERY, Douglas C, Cheryl L JENNINGS a Murat KULAHCI. Introduction to time series analysis and forecasting. Wiley-Interscience, c2008, xi, 445 s., 2008. ISBN 04-716-5397-7.
-
Wooldridge, J.M. Introductory econometrics: a modern approach. Boston: Cengage Learning, 2016. ISBN 978-1-305-27010-7.
|