Attended -- Statistical Data Analysis training

The course focused on broad range of data analysis and data wrangling topics. Dr. Huihui Li was the focal person sharing her expertise in the field of Quantitative genetics working the way through typical scenario of data import to inference. Although it was earlier touted that the session will mostly dwell on the analytical aspects of plant breeding datasets, in her efforts to making sure trainees get the basics and have a good exploratory mindset, Dr. Huihui very enthusiastically demonstrated a typical Microsoft excel workflow of getting most information out of data (often times messy as it was available). One aspect of her presentation I loved in particular was the emphasis on the kind of thought process one requires to tackle different sorts of data – those from replicated complete block, replicated incomplete block and replicated multi-environment trial designs. She made it perfectly clear that in modern data analytics workflow, understanding of data model and specification of it’s correct form is absolutely essential. During later period of the session, we got into the inner workings of linear mixed models and their application in deriving inference from designed field experiments. Overall, the training was very successful in provoking a scientific thinking. Many thanks to organizers.

The focus was on following topics:

• Statistics
• Training
• Mixed-models