Universität Wien
Warning! The directory is not yet complete and will be amended until the beginning of the term.

400018 SE Hierarchical Modelin for Social Scientists' (2017W)

SE Methods for Doctoral Candidates

Continuous assessment of course work

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 15 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

  • Monday 22.01. 09:00 - 12:00 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Monday 22.01. 14:00 - 16:30 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Tuesday 23.01. 09:00 - 12:00 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Tuesday 23.01. 13:00 - 15:00 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Wednesday 24.01. 09:00 - 12:00 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Wednesday 24.01. 14:00 - 16:30 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Thursday 25.01. 09:00 - 12:00 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Thursday 25.01. 15:15 - 17:45 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien
  • Friday 26.01. 09:00 - 12:00 C0628A Besprechung SoWi, NIG Universitätsstraße 7/Stg. III/6. Stock, 1010 Wien

Information

Aims, contents and method of the course

• 1. General introduction and course-specific refresher.

- OLS.
- Interactions with dichotomous variables.
- Binary models.

• Lab I

- Introduction to RStudio.
- Reading in data and manipulating it.
- Estimating linear models.

• 2.. Linear Hierarchical Modeling

- What ate random effects?
- Varying intercept models.
- Models with systematically varying intercepts.
- Measures of model quality.

• Lab II
- Implementing all learned concepts from part 2 in RStudio
• 3. Hierarchical Modeling with Cross-Level Interactions

- Hierarchical modeling with cross-level interactions.
- Hierarchical modeling with binary models.
- Non-nested models.

• Lab III

- Implementing all learned concepts from part 3 in R

• 4. Advanced Topics - Multilevel Regression and Post-Stratification (MrP)

- Survey methods for sample selection.
- How hierarchical modeling can help (--+ MrP).
- Further developments: Deep interactions, synthetic post-stratification (MrsP).

• Lab IV

- Estimating response rriodels.

- Weighting predicted probabilities for ideal types.
- Generating small sample measurements.

• 5. Advanced Topics - Bayesian Hierarchical Modeling

- Quick theoretical introduction to Bayesian statistics.
- How and when can a Bayesian model outperform frequentist apporaches?

• Lab V

- Setting up a model in Stan.
- Re-estimating prior models with convergence problems.

Assessment and permitted materials

Minimum requirements and assessment criteria

Final test (70%) and participation during course (30%)

Examination topics

Reading list

Gelman and Hill, Data Analysis Using Regression and Multilevel/Hierarchical Models

Association in the course directory

Last modified: Mo 07.09.2020 15:47