Бакалавриат
2025/2026
Временные ряды
Статус:
Курс по выбору (Международная программа по бизнесу и экономике)
Кто читает:
Департамент экономики
Где читается:
Санкт-Петербургская школа экономики и менеджмента
Когда читается:
3-й курс, 3 модуль
Охват аудитории:
для своего кампуса
Язык:
английский
Кредиты:
3
Контактные часы:
32
Course Syllabus
Abstract
The course is devoted to methods and models of analysis and forecasting of time series. The specific results of this discipline are the familiarization of methods for identifying non-stationarity and reducing time series to a stationary one, building AR, MA and ARMA time series models, volatility models, identifying and analyzing structural breaks in data, building VAR models for multivariate time series, ARDL-models, forecasting by specified models, time series cointegration analysis and building VECM-models. The study of this discipline is based on the following disciplines: Probability Theory, Statistics, Econometrics. The main provisions of the discipline should be used in the future when studying the discipline of Risk Management, Financial Risk management, Quantitative methods in finance, as well as in the preparation of term paper and bachelor's thesis.
Learning Objectives
- The aim of the course is to develop students' competencies in the analysis and forecasting of univariate and multivariate time series.
Expected Learning Outcomes
- Can calculate simple and logarithmic growth rates. Student is able to adjust the time series for inflation and to identify seasonality. Able to measure the presence of autocorrelation in time series (ACF, Ljung-Box test). Able to conduct stationarity tests: ADF, KPSS, PP. Student is able to reduce the time series to a stationary series. Students know appropriate RStudio packages and commands
- Knows the basic models of data generation and types of processes. Knows the properties of AR, MA and ARMA models
- Able to evaluate the parameters of the AR, MA, ARMA model. Able to test the ARCH effect in the residuals
- Able to choose the order and estimate ARDL-models
- Able to evaluate the order and evaluate the parameters of ARCH and GARCH models. Able to use these models for forecasting. Knows other specifications of volatility models: GARCH-M, EGARCH, TGARCH and so on
- Able to conduct tests for the presence of structural breaks in the data
- Able to test time series for the presence of cause-and-effect relationships. Able to evaluate the order and parameters of the vector autoregression model. Able to calculate impulse response functions (IRF)
Course Contents
- 1. Introduction to time series analysis. AR, MA, ARMA, ARIMA processes
- 2. Specification selection and estimation of ARMA models
- 3. ARDL model. Forecasting AR(p), MA(k) and ARMA(p, k) processes
- 4. Modeling volatility. ARCH and GARCH models
- 5. Nonlinearity in mean: structural breaks
- 6. Multivariate time series: vector autoregression (VAR) model
- 7. Analysis of non-stationary series. Cointegration and vector error correction model (VECM)
Assessment Elements
- Lectures’ attendanceRoll call or census of students at lectures
- Activity on seminars
- Control Work
- Exam
Interim Assessment
- 2025/2026 3rd module0.25 * Activity on seminars + 0.3 * Control Work + 0.4 * Exam + 0.05 * Lectures’ attendance
Bibliography
Recommended Core Bibliography
- Enders, W. (2015). Applied Econometric Time Series (Vol. Fourth edition). Hoboken, NJ: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1639192
- Tsay, R. S. (2010). Analysis of Financial Time Series (Vol. 3rd ed). Hoboken, N.J.: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=334288
Recommended Additional Bibliography
- Введение в эконометрику : Учебник для вузов, Сток, Дж., 2015