Магистратура
2026/2027
Эконометрика
ID 1163580
Статус:
Курс обязательный (Аналитика данных для бизнеса и экономики)
Кто читает:
Департамент экономики
Где читается:
Санкт-Петербургская школа экономики и менеджмента
Когда читается:
1-й курс, 2, 3 модуль
Охват аудитории:
для своего кампуса
Преподаватели:
Заздравных Евгений Александрович
Язык:
английский
Кредиты:
6
Контактные часы:
60
Course Syllabus
Abstract
This course provides an introduction to the main theoretical and applied tools of modern econometrics. It covers probability and statistical foundations, linear regression, model interpretation and specification, heteroskedasticity and autocorrelation, endogenous regressors, instrumental variables, GMM, maximum likelihood, limited dependent variable models, and non-parametric methods.
The course combines econometric theory with practical applications, emphasizing the assumptions underlying estimation and inference and the interpretation of empirical results. Students will develop the ability to formulate econometric models, evaluate their validity, and apply appropriate estimation and inference methods to economic data.
Learning Objectives
- - To provide a comprehensive theoretical and applied foundation in modern econometric methods, ranging from classical linear regression to advanced techniques such as instrumental variables, maximum likelihood, and non-parametric approaches. - To develop students' ability to critically evaluate the assumptions underlying econometric models and to select appropriate estimation and inference procedures for empirical economic data. - To bridge the gap between econometric theory and practical data analysis, enabling students to interpret empirical results meaningfully and to communicate findings effectively in a business analytics context.
Expected Learning Outcomes
- - Formulate and estimate linear regression models using Ordinary Least Squares (OLS), interpret coefficients and marginal effects, and critically assess the validity of the underlying classical assumptions.
- - Diagnose and correct for violations of regression assumptions, including heteroskedasticity, autocorrelation, and functional form misspecification, by applying appropriate robust inference procedures and model transformations.
- - Address endogeneity challenges by justifying the use of instrumental variables, applying two-stage least squares (2SLS) and Generalized Method of Moments (GMM), and evaluating instrument validity (relevance and exogeneity).
- - Apply maximum likelihood estimation to econometric models, derive and interpret parameter estimates for models with limited dependent variables (e.g., binary response using Logit/Probit), and differentiate these from the linear probability model.
- - Compare and contrast parametric and non-parametric econometric approaches, and implement kernel-based non-parametric regression methods to model flexible functional relationships when appropriate.
- - Critically evaluate empirical research and communicate econometric findings—including estimation results, diagnostic tests, and causal interpretations in a clear and rigorous manner suitable for business analytics and policy decision-making
Course Contents
- 1. Probability and Statistical Foundations
- 2. Introduction to Linear Regression
- 3. Interpreting and Comparing Regression Models
- 4. Heteroskedasticity and Autocorrelation
- 5. Endogenous Regressors, IV, and GMM
- 6. Maximum Likelihood
- 7. Models with Limited Dependent Variables
