E634: Hadley Wickham, RStudio Chief Scientist & open source pioneer, on breakthroughs in data science, visualization, statistics & the biggest philosophical questions facing humanity



about this episode

The world has become flooded with data over the past 10 to 20 years. Hadley Wickham, Professor of Statistics at Rice University and Chief Scientist at RStudio, explains the most efficient ways to sort through the oceans of useless data and find what you’re looking for. Hadley became a rockstar in the world of data science by creating a package called ggplot2, which turns data into visualizations. Jason and Hadley also discuss the process of “open writing” in modern technical journals. Then, Jason shares his desire to make predictions, and hopes that Hadley can share some advice on how to utilize statistics to make accurate predictions as an investor. But the conversation pivots towards the big philosophical questions… “Is God in the data?”


0:39-1:55: Jason gives an introduction to the subject of data, and our guest, Hadley Wickham.

1:55-3:13: Jason and Hadley discuss the importance of data, and how that importance has grown in the past 10 to 20 years.

3:13-6:33: Hadley explains how sports recruitment and team management has been among the most notable changes due to data collection. And also… cows?

6:33-12:18: Hadley explains why it’s more important to get the right data vs. more data.

12:18-18:49: Hadley gives a bit of background on his open source project, RStudio. He then shares some examples of the visualizations that his program is famous for.

18:49-21:54: Jason brings up the issue of people dismissing arguments in the face of real data. Hadley points out that humans need a narrative to be convinced of something, the data is actually not as important to a lot of people.

21:54-23:52: Where should we be investing the most in data science? Hadley believes education should be the focus.

23:52-25:36: Jason and Hadley discuss the use of data in self-driving cars and the difference between statistics and machine learning.

25:36-31:35: Hadley explains the process of “open writing.”

31:35-35:17: Jason asks Hadley more about his company and their small venture backing, as well as education in data science.

35:17-39:56: Who are the main contributors to RStudio as an open source community? And how does governance work?

39:56-44:24: Jason asks about prediction, specifically how he can utilize statistics to make accurate predictions as an investor.

44:24-48:54: Jason: What questions do you want to solve most? Hadley: Happiness…

48:54-53:09: The questions start to get deep… “Is God in the data?”

53:09-57:04: Hadley gives some background on how he got into statistics and the difference between introverts and extroverts.

57:04-59:59: How do we deal with the impending job extinction through technology?

59:59-1:03:55: Jason tries to convince Hadley to take up poker.

more episodes