"Tame" data principles and the fivethirtyeight R package

Tuesday, June 12th, 20182:00 pm – 3:00 pm ET

Presented by: Albert Y. Kim (Amherst/Smith College)


FiveThirtyEight.com is a data journalism website founded by Nate Silver that makes many of the datasets used for their articles openly available on GitHub.com. The fivethirtyeight R package acts as an intermediary to make all this data, its documentation, and links to the original articles easily accessible to R users. Furthermore, the package "tames" the data: the data is pre-processed enough so that the biggest barriers to data exploration faced by novice R users are eliminated, but not so much that the true nature of the data as it exists "in the wild" is completely betrayed. In this webinar, I will present the corresponding set of "tame" data principles, discuss the pedagogical thinking behind them, and present illustrative examples involving datasets from articles on FiveThirtyEight.com.