Freie Plätze:

Termin/e:
09.04.2021, 10:00 - 13:15 Uhr
16.04.2021, 10:00 - 13:15 Uhr
An- und Abmeldefrist:
07. April 2021 00:00 Uhr

Abmeldefrist
26. März 2021 23:55 Uhr

Format: Online
Stornierungsgebühr:
€50,00
Beschreibung



 

Webinar: Introduction to Multilevel Modelling

 

 

 

Students in classrooms, regions in countries, cross-national surveys are just a few examples of multilevel data structures. All of them have one problem in common. The observations are not independent of each other because of the clear clustering within the data causing potential problems with autocorrelation. Researchers need to do something about this and control for the potential heterogeneity across the clusters otherwise their regression results will certainly be biased. Multilevel modelling comes to the rescue, though it is not the best solution in all instances. In this course, you will learn the most common solutions to the problem including an in-depth introduction to how multilevel models work.

 

 

 

Target Group

 


This course is targeting scientists from different disciplines and researchers at all levels of their career who have a solid foundation regression and logistic regression and who would like to extend their knowledge to include the basics and application of multilevel modelling.

 

(A solid foundation is one that goes beyond knowing what to click in the software and what numbers to copy from the output into the table. Let’s say, if you know why heteroskedasticity and autocorrelation are problematic in the regression framework and you want to do something about it, you are ready for your first multilevel modelling course. If you have conducted regression before but you are unsure about this, an in-depth course in regression is what your trainer would recommend before this workshop.)

 

 

 

Objectives

 

 

  • Participant will learn why unmodelled heterogeneity is a problem and go through multiple ways of modelling such heterogeneity.
  • Models covered will include
    • fixed effects regression models, modelling variance of slopes and intercepts in regressions
    • hierarchical linear, mixed effects and multilevel models
    • continuous and limited dependent variable models such as binary-logistic, ordered and count regressions.
  • Finally, participants will explore modelling multiple sources of heterogeneity simultaneously.

 

 

 

Content
 

 

Day 1

  • What are Multilevel Models
  • Heterogeneity in the Regression Framework
  • Building Blocks of Multilevel Models
  • Navigation of the Jargon and Terminology
  • Estimation
  • Model Building Approaches
  • Model Fit

 

Day 2

  • Centering and separating impact across the levels of analysis
  • General Linear Mixed Models (Binary-logistic, ordered and count dependent variables)
  • Cross-classification
  • What else is out there (where you can go from this point forward)

 

 

 

Methods

 

 

  • Examples for the workshop will be in R. Very basic R knowledge (how to load data, how to run a regression) is recommended, though the examples will still make sense without it but will be hard to reproduce with one’s own data.
  • Stata code closely resembling the examples will be provided.
    • Note: Instructor does not use Stata. But past students passed on Stata code

 

 

 

Location, Date and Time

 


Friday, 9 April 2021, 10.00 am - 1.15 pm
Friday, 16 April 2021, 10.00 am - 1.15 pm

 

Note on the course format: This course was designed for a pandemic friendly online delivery. Before the two live sessions you will be asked to watch multiple video lectures and to read readings, which your trainer will provide you with in advance. In addition you will be asked to interact with fellow participants about the readings and to record a video, i.e. with you mobile phone, introducing yourself and the kind of research problems you wish to apply multilevel modelling to (and share this video with others). While meetings are limited (as who wants to sit on Zoom all day) the workload with all the above matches a typical two full day workshop, so please plan accordingly.

 

 

 

Technical Requirements (Amendment on 18 March 2021)

 

 

Zoom
The live sessions of the webinar will be held via Zoom. All participants will receive the access link with our reminder e-mail one week before the workshop. For information on using Zoom click here.

 

Panopto - https://www.panopto.com/privacy/:
On this platform, your trainer will provide the video lectures via links. (No download and no individual account necessary.)

 

MS Teams
This platform can be used to interact in general and about the readings.
All participants will receive the required information with our reminder e-mail one week before the workshop. For information on using MS Teams click here.


The trainer will provide you with instructions and information on how to use the platform (Panopto).

 

Software R and RStudio:
The software is needed for practice purposes outside of the live sessions. Alternatively, you can also work in Stata. Depending on where you are attending the webinar from, the following options are available to you.

 

On campus, from your office workstation: You can download R and RStudio from the IT-SERVICES Software Center to your stand PC or your WU laptop.

 

At your home office:

  • WU laptop: You can download R and RStudio from the IT-SERVICES Software Center to your WU laptop via a vpn connection. You can find further information here: https://www.wu.ac.at/it/services/network/vpn/?no_cache=1
  • WU laptop or private device: A remote desktop connection allows you to remotely control your work computer at WU. You can use files and software programs, including R and RStudio, as if you were there in person, or you can download R and RStudio from the Software Center to your work computer and use it at home. For further information, please follow this link: https://swa.wu.ac.at/Serviceeinrichtungen/it-services/Seiten/Content/ICE/Homeoffice%20nach%20R%C3%BCcksprache.aspx#Fernzugriff_einrichten. However, when using R and RStudio via the remote desktop connection and simultaneously using the video chat function of Zoom, the video and camera function of the laptop or stand PC at home will not be accessed, but the video and camera function of the office device will be in use via the remote connection. In order to avoid this, when using R and RStudio via the remote connection, you would have to install Zoom on a 2nd device (e.g. tablet) and follow the webinar in the Zoom video chat via this device.
  • R is an open source software while RStudio is an integrated development environment for R. If you have not installed them yet, they can be downloaded to a private laptop at https://cran.r-project.org./ and  https://rstudio.com/products/rstudio/download/. More information on installing R and RStudio can be found at e.g. https://rstudio-education.github.io/hopr/starting.html.

 

 

 

Fees and Registration

 

 

This workshop is open to a limited number of participants. The registration deadline is 26 March 2021.

 

Please note that you should notify us before the registration deadline if you are unable to attend the workshop. Otherwise the full fee will be charged. Please let the Personnel Development and Planning Office know if you will not be attending. There are often waiting lists for the workshops, and this will give one of your colleagues the chance to attend. In addition, if we can fill the vacancy with someone from the waiting list, no cancellation charges will apply for you.

 

To sign up for this workshop, please click "Register" at the bottom of this page. By registration for this workshop, you accept our terms and conditions “Workshop and Event Registration Information Sheet”. Further information on the collection of personal data can be found in the “Data Protection Statement” on our homepage.

 

For any further information please contact Nina Rath (Nina.Rath@wu.ac.at, Ext. 6173).

 

The course fee is €40.

 

 

 

Trainer

Levente Littvay, PhD

Levente (Levi) Littvay is Professor of Political Science at Central European University where his teaching includes research design, applied statistics and is the recipient of CEU's Distinguished Teaching Award. Received his MA and PhD in Political Science and MS in Survey Research and Methodology from the University of Nebraska-Lincoln. As one of the Academic Convenors of the European Consortium for Political Research Methods Schools he taught numerous introductory and advanced research methods workshops including regression from intro to advanced levels, causal inference, program evaluation, measurement, missing data, multilevel modeling, structural equation modeling and multilevel structural equation modeling. Member of the European Social Survey’s Round 10 (2020-21) Democracy and COVID19 module questionnaire design teams and co-PI of the Comparative Study of Election Systems for Hungary and Tunisia. A former Fernand Braudel Fellow of the European University Institute. Has publications in Social Justice Research for which he received the Morton Deutsch Award for best article in 2017, Political Analysis, The Journal of Politics, Political Research Quarterly, Political Psychology, BMC Medical Research Methodology, and along with other medical journals, in Twin Research and Human Genetics where he is Associate Editor for Social Sciences. He is Specialty Chief Editor for Methods and Measurement at Frontiers in Political Science. His books include Multilevel Structural Equation Modeling with Bruno Castanho Silva and Constantin Manuel Bosancianu in SAGE QASS (little green book) series.