|
Lecturer(s)
|
-
Vencálek Ondřej, doc. Mgr. Ph.D.
-
Fačevicová Kamila, Mgr. Ph.D.
-
Pavlů Ivana, Mgr. Ph.D.
|
|
Course content
|
1. Specifics of time series analysis, evaluation of prediction quality. 2. Modeling of time series trends using mathematical curves: constant, linear, quadratic trend, exponential, shifted exponential, logistic, Gompertz trend. 3. Adaptive methods for time series trend modeling - moving averages method, exponential smoothing. 4. Modeling the seasonal component of time series - regression approach, model of hidden periods, Holt-Winters method. 5. Random component analysis (randomness tests). 6. Box-Jenkins methodology: MA, AR, ARMA, ARIMA, and SARIMA processes.
|
|
Learning activities and teaching methods
|
|
Lecture, Dialogic Lecture (Discussion, Dialog, Brainstorming), Demonstration
|
|
Learning outcomes
|
The aim is to acquaint students with the basic procedures in the analysis of time series.
The student will be able to independently analyze a time series, make a prediction in this time series and evaluate the quality of this prediction.
|
|
Prerequisites
|
Basics of probability theory and statistics.
|
|
Assessment methods and criteria
|
Oral exam, Seminar Work
Credit: active participation, seminar work Exam: oral
|
|
Recommended literature
|
-
Arlt, J., Arltová, M. (2007). Ekonomické časové řady. Grada, Praha.
-
Cipra, T. (1986). Analýza časových řad s aplikacemi v ekonomii. SNTL, Praha.
-
Hindls R., Hronová S., Seger J., Fischer J. (2007). Statistika pro ekonomy. Professional Publishing.
-
Hyndman, R.J., Khandakar, Y. (2008). Automatic Time Series Forecasting: The forecast package for R. Journal of Statistical Software, 27(3).
-
Tetlock, P. E., Gardner, D. (2016). Superprognózy ? umění a věda předpovídání budoucnosti. Jan Melvil, Brno.
|