Athlete Monitoring: Data Analysis and Visualization
In this module, I am covering foundational topics that are needed to progress this course to more practical data wrangling, analysis, and visualization. This step, and the underlying assumptions, are usually jumped over in favor of some fancy and flashy graphs and dashboards. But as the old saying goes: “garbage in, garbage out”, we need to watch what goes into our models and visualization, and more importantly what assumptions are we making and how we are dealing with common scenarios (i.e., data aggregation, missing data treatment and so forth).
In this module we are going to cover the following topics:
- Scale types (nominal, ordinal, interval, ratio)
- Data formats (wide and long)
- Missing data (missing at random, missing not at random, completely missing at random)
- Tags (attendance, athlete health and training status, session type and context)
- Aggregation (aggregating data that is on different unit of analysis)
- Rolling functions (smoothing, acute, chronic, ratios)
- Nominal rolling functions (rolling nominal variables, like low-medium-high)
- Normalizing individuals (high vs low raters, highly variable vs. low variable rates)
- Comparing individuals to group (group median and IQR, group trends vs. individual trends)
This module is quite dense, so grab a coffee and let’s go!