Basic and Advanced Multilevel Modeling with Stata

Prerequisites (knowledge of topic)

A graduate statistics course, at an introductory level, with exposure to regression analysis.

 

Hardware

Provided by host institution, however it is highly recommended to bring your own laptop

 

Software

Provided by host institution

 

Course content

 

Day 1 (Morning Session): A brief introduction to Stata

 

Day 1 (afternoon session): Fitting single-level regression models using Stata

 

Day 2 (morning session): Why do we need multilevel and mixed models?

 

Day 2 (afternoon session): The intra-class correlation coefficient and its estimation

 

Day 3 (morning session): How many levels? – Proportion ofthird level variance and its evaluation

 

Day 3 (afternoon session): Robust modeling of lower-level variable relationships in the
presence of clustering effect

 

Day 4 (morning session): Mixed effects models (mixed models)

 

Day 4 (afternoon session): Mixed models with discrete responses

 

Day 5 (morning session): Longitudinal multilevel modeling

 

Day 5 (afternoon session): Extensions, Limitations, Conclusion and Outlook.

 

Literature

Mandatory:

Supplementary / voluntary:

 

Mandatory readings before course start:

 

Examination part

Take home assignment, to be submitted within 3 weeks upon course completion.

 

Participants are allowed any literature they can find, incl. the lecture notes volume to be provided in pdf form to them before course commences.

 

Supplementary aids

Course participants are allowed to use any literature they can access, incl. the lecture notes.

 

Examination content

Multilevel modeling with missing data, violations of missing at random, and accounting for clustering effects.

 

Literature

Raykov, T. (2019).  A course in multilevel modeling.  Lecture notes.  Michigan State University, East Lansing, Michigan, USA.