Transformations: The good, the bad, the ugly
The good about data transformations is that they readily bring the data close to the assumptions necessary for model building and interpretation. The bad is that, deciding which transformation to use can sometimes be frustrating if the effects are not observed. In addition if wrongly applied they might lead to bias in inference. The ugly fact about transformations is that they are buried in the very core of may subject areas that they are blindly applied without paying attention to the missed opportunities of using the raw data or other approaches. In this seminar, an attempt will be made to shift the Adhoc paradigms onto more intuitive/alternative approaches to data modifications.
Practical information:
Georganiseerd door:
Teacher / speaker
Emmanuel Abatih
Emmanuel Abatih is a post-doctoral research fellow at Ghent University and he works as the FLAMES coordinator for UGent and as a statistical consultant for FIRE and DASS. He obtained a PhD in Epidemiology and Biostatistics in 2008 at the University of Copenhagen on the topic: “Assessment of the impact of the non-human use of Antimicrobial Agents on the Selection, Transmission and Distribution of Antimicrobial Resistant Bacteria” . He worked for the Institute of Tropical Medicine (ITM) in Antwerp, as a post doc statistician on topics including: space-time analysis, diagnostic test elevation, transmission dynamic modeling and risk analysis. He also served as a statistical consultant for the TB, Malaria and Parasitology units of the ITM. He has supervised/co-supervised over 30 masters and 7 PhD students. He has been teaching courses ranging from general statistics to more specialized areas like Machine Learning, Causal Inference and Structural Equations Modeling. He has experience with R, python, SPSS and STATA.
Related courses
Summer School on Security and Privacy in the Age of AI
Summerschool - Heverlee - KU Leuven, UGent, VUB, Imec