Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Member rate £492.50
Non-Member rate £985.00
Save £45 Loyalty discount applied automatically*
Save 5% on each additional course booked
*If you attended our Methods School in the July/August 2023 or February 2024.
Friday 3 March: 13:00-15:00 and 15:30-17:00
Saturday 4 March: 09:30-12:00 and 13:00-14:30
7.5 hours over two days
The goal of the course is to help people who are tortured by constant missing data problems. Sometimes it feels wrong to throw away so much information just because a person did not respond to a single question on a survey. Well, it is wrong and powerful methods exist to overcome the problem. To best handle missing data, we should develop a solid theoretical understanding of missing data and this will lead us to the best solutions to the problem. Some commonly used missing data treatments are certainly going to produce bias, others have a fairly good chance of producing unbiased results. More importantly, in the presence of missing data, some treatment is always applied to deal with the problem. Software defaults and intuitive solutions often are not the best ways to fix the problem. This course will teach participants how to think about missing data and how to fix, or, at least, best deal with their missing data problems for inferential statistical models.
Levente Littvay researches survey and quantitative methodology, twin and family studies and the psychology of radicalism and populism.
He is an award-winning teacher of graduate courses in applied statistics with a topical emphasis in electoral politics, voting behaviour, political psychology and American politics.
He is one of the Academic Convenors of ECPR’s Methods School, and is Associate Editor of Twin Research and Human Genetics and head of the survey team at Team Populism.
Linear and Logistic Regression with Assumptions Tests. Basic Knowledge of R. Basic knowledge of Maximum Likelihood Estimation
Day | Topic | Details |
---|---|---|
Friday Afternoon | • How to think about missing data • Classical soltutions and what is wrong with them • Introduction to Modern Missing Data Solutions |
http://media.wiley.com/product_data/excerpt/65/04711838/0471183865.pdf (Pretty hard reading, but important.) http://folk.ntnu.no/slyderse/medstat/KLMED8006/Shafer.pdf (READ FOR SURE) Enders. Applied Missing Data Analysis Ch1-4 + 7-8 (maybe 6) (Optional) Allison. Missing Data. (An easy short intro) |
Saturday Morning | • More in depth assessment of Full information maximum likelihood estimation and multiple imputation (with practical) • Exploiting Auxiliary Variables |
https://methodology.psu.edu/media/techreports/01-48.pdf (Useful for SEM) Enders Ch5 (Optional) Amelia II Manual. Zelig Manual. (Useful references) |
Saturday Afternoon | • Advanced Topics (maybe not all of these) - Unit nonresponse and weighing solutions to the missing data problem - To impute the dependent or not to impute the dependent - Interactions and squares - Statistical Models without Statistical Inference - Models for data Not Missing At Random - Advanced Models (SEM, MLM, Longitudinal Models) - Planned Missing and Merged Datasets - Causal Inference as a Missing Data Problem - Simulation Studies for Missing Data |
All optional: https://arxiv.org/pdf/1605.01095.pdf https://lbj.utexas.edu/sites/default/files/file/news/Transform%20then%20impute.pdf http://hrcak.srce.hr/file/105184 Enders (the rest) |
R and SPSS
Anything that can run the above. (You can bring your own laptop and install the two-week demo of SPSS even.)