Магистратура
2019/2020
Анализ лонгитюдных данных
Лучший по критерию «Полезность курса для Вашей будущей карьеры»
Лучший по критерию «Полезность курса для расширения кругозора и разностороннего развития»
Лучший по критерию «Новизна полученных знаний»
Статус:
Курс по выбору (Прикладная статистика с методами сетевого анализа)
Направление:
01.04.02. Прикладная математика и информатика
Где читается:
Международная лаборатория прикладного сетевого анализа
Когда читается:
2-й курс, 3 модуль
Формат изучения:
без онлайн-курса
Преподаватели:
Кускова Валентина Викторовна
Прогр. обучения:
Прикладная статистика с методами сетевого анализа
Язык:
английский
Кредиты:
4
Контактные часы:
48
Course Syllabus
Abstract
This course is about quantitative methods, namely statistics, applied to social sciences. Specifically, we will focus on certain statistical competencies that help evaluate processes over time. I expect you to understand the basics of statistics you’ve learned previously in this course; everything else we will learn in this class. As you will see, we will use a lot of real-world datasets, and I am concerned more with your understanding on how statistic works as opposed to memorizing the formulas. This class will be unique in a sense that I will bring a lot of non-statistical material to help you understand the world of decision sciences.
Learning Objectives
- The course gives students an important foundation to develop and conduct their own research as well as to evaluate research of others.
Expected Learning Outcomes
- Know the theoretical foundation of longitudinal analysis.
- Be able to understand the meaning and use of longitudinal models.
- Know modern applications of longitudinal analysis.
- Know the variety of time-series models that are available to analyze real-life problems, starting with the simple OLS regression and ending with highly advanced models.
- Be able to present and/or interpret data in tables and charts.
- Have an ability to use computer software to perform statistical analysis on data (specifically, STATA).
- Be able to understand and apply descriptive statistical measures to real-life situations.
- Be able to understand and apply probability distributions to model different types of social processes.
- Have an ability to forecast future numbers based on historical data.
- Have an ability to resolve problems and recognize the most common decision errors and make tough decisions in a competent way.
Course Contents
- Introduction to the Framework of longitudinal data analysisThe Where, Why, and How of Longitudinal Data. Simple Linear Regression Model – A Review
- Basics of Time Series IBasics of Time Series Analysis. Static and Finite Distributed Lag models.
- Basics of Time Series IITrending, non-stationarity, serial correlation. Autoregressive (AR) proves and moving average (MA) process.
- ARIMAAutoregressive integrated moving average model (ARIMA) with extensions. Box-Jenkins meth-od for working with ARIMA.
- Advanced time-series models ICointegration. Equilibrium. Engle-Granger two-step procedure. Error correction models (ECM) and vector autoregression models (VAR). Reduced form VAR. Lag length selection and infor-mation criterion.
- Advanced time-series models IIStructural vector autoregression models, including short-run (SVAR). Long-run restrictions. Structural equation models (SEM). The state-space approach to time series analysis. Predicted states, filtered states, smoothed states, forecasting.
- Advanced time-series models IIITime-series with categorical predictors. Binary response. Random vs. fixed effects. Mixed model assumptions and estimation. Non-linear mixed effects. Observed marginal proportions, proportional and non-proportional odds.
- Advanced time-series models IVPanel and time series cross-sectional data (TSCS). Benefits of time-space data. Variable interceps and slopes. Errors in the TSCS models. Heterogeneity and pooling. Fixed and random effects estimation.
Assessment Elements
- Final In-Class or Take-home exam (at the discretion of the instructor)
- Quizzes (Best 9 of 10, Varied points)
- In-Class Labs (9-10 x Varied points)
- Homework Assignments (5 x Varied points)
Interim Assessment
- Interim assessment (3 module)0.5 * Final In-Class or Take-home exam (at the discretion of the instructor) + 0.2 * Homework Assignments (5 x Varied points) + 0.2 * In-Class Labs (9-10 x Varied points) + 0.1 * Quizzes (Best 9 of 10, Varied points)
Bibliography
Recommended Core Bibliography
- Analysis of financial time series, Tsay, R. S., 2005
- Derryberry, D. R. (2014). Basic Data Analysis for Time Series with R. Hoboken, New Jersey: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=817454
- Montgomery, D. C., Jennings, C. L., & Kulahci, M. (2015). Introduction to Time Series Analysis and Forecasting (Vol. Second edition). Hoboken, New Jersey: Wiley-Interscience. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=985114
- Taris, T. (2000). A Primer in Longitudinal Data Analysis. London: SAGE Publications Ltd. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=251795
Recommended Additional Bibliography
- Beran, J. (2017). Mathematical Foundations of Time Series Analysis : A Concise Introduction. Cham, Switzerland: Springer. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1741935
- Franses, P. H., & Paap, R. (2004). Periodic Time Series Models. Oxford University Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsrep&AN=edsrep.b.oxp.obooks.9780199242030
- Palma, W. (2016). Time Series Analysis. Hoboken: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1229817