Understanding Messy Time Series Data [Gear-Up]

This workshop introduces you to working with messy time series data. We will teach you about common pitfalls for data sourcing and continuity through use of Gross Domestic Product (GDP) as a rough measure of global societal well-being. The first hour will introduce GDP to discuss these issues when different reporting agencies, incentives, and approaches are considered.

The second hour will dive into code that compares results of different models based on endogenous and exogenous data filling methods, along with useful guidance on tools for vectorized approaches to your data. Basic Python proficiency is assumed if you want to run the examples, but all are welcome to attend and learn about data robustness issues and how the concepts might be useful to apply to your own data and research.

If you want to learn basic Python, visit us at https://ssds.stanford.edu to register for the upcoming Text Analysis and Machine Learning (TAML) Bootcamp (September 19, 21, and 23) or Introduction to Python workshop (October 5). 

Instructors: Anthony Weng and Evan Muzzall

This is a hybrid workshop. Upon registering you can select to attend in-person at the Li & Ma Science Library in the SAPP Center or via Zoom.