This workshop is about the various techniques available in Python (from scipy, statsmodels, sklearn) for handling ill conditioned data sets. A new new generalized method will also be introduced. We will walk through examples of what ill conditioned data are - more common occurrence when dealing with big data sets and variables are correlated - the consequences of such data, and the methods available.
Katya works on data problems in developing countries. Her main areas of interest are in social networks and the spread of information, conducts randomized trials and has interest in developing new empirical techniques. She has a PhD in Applied Economics and a BA in Math in Economics.