2024/2025
Многоуровневый регрессионный анализ
ID 801044
Лучший по критерию «Полезность курса для расширения кругозора и разностороннего развития»
Лучший по критерию «Новизна полученных знаний»
Статус:
Маго-лего
Кто читает:
Департамент социологии
Когда читается:
4 модуль
Охват аудитории:
для всех кампусов НИУ ВШЭ
Преподаватели:
Настина Екатерина Александровна
Язык:
русский
Кредиты:
3
Программа дисциплины
Аннотация
Social researchers often have to address the influence of the social context on individual behavior and attitudes, which requires combining different levels of analysis. This course is devoted to multilevel regression, a method developed for analyzing such multilevel or "nested" data, where classical regression methods can lead to biased estimates. The course covers the basic principles of this method (fixed and random effects, cross-level interactions, model fit assessment, etc.), which are illustrated using examples from international comparative studies. The workload of the course includes participation in lectures and seminars, group work with open data from international surveys, independent readings, as well as an individual project in the form of an essay, which can later be developed into a research article. Successful completion of the course requires a basic understanding of the fundamentals of linear and logistic regression modeling, as well as proficiency in R.
Цель освоения дисциплины
- Develop a solid understanding of multilevel data and mixed effects.
- Сultivate hands-on skills in specifying, estimating, and selecting multilevel models using R
- Build skills in analysis, visualization, and presentation of multilevel modeling results to solve applied research questions.
Планируемые результаты обучения
- Students are able to access the results of multilevel modeling and interpret them statistically and sociologically.
- Students model individual cases within groups choosing the best model.
- Students understand the basic principles of multilevel modeling
Содержание учебной дисциплины
- Topic 1. Introduction. The idea of hierarchical modeling. Pre-requisites for multilevel modeling. Alternatives to multilevel modeling.
- Topic 2. A basic (empty) multilevel model. Intra-class correlation coefficient. Individual-level predictors. Group - level predictors. Fixed intercept. Fixed slopes
- Topic 3. Varying intercepts. Varying slopes. Cross-level interaction in multilevel models
- Topic 4. Multilevel binary logistic regression
- Topic 7. Class discussion of issues in individual projects prior to submission
- Topic 6. Testing and model specification, model comparisons
- Topic 5. Mid-term exam and research proposals Q&A
Элементы контроля
- Individual research project essay in English (final project)
- Mid-term exam
- Homework Assignments
- Seminar quizes
Промежуточная аттестация
- 2024/2025 4th module0.1 * Seminar quizes + 0.25 * Mid-term exam + 0.4 * Individual research project essay in English (final project) + 0.25 * Homework Assignments
Список литературы
Рекомендуемая основная литература
- Data analysis using regression and multilevel/hierarchical models, Gelman, A., 2009
- Handbook of multilevel analysis, , 2008
Рекомендуемая дополнительная литература
- Multilevel analysis : an introduction to basic and advanced multilevel modeling, Snijders, T. A. B., 1999
- Multilevel modeling of social problems : a causal perspective, Smith, R. B., 2011