Putting science into data science

Thinking Clearly with Data: A Guide to Quantitative Reasoning and Analysis. Book and course by Bueno de Mesquita & Fowler. Intro to data science emphasizing critical thinking over statistical techniques.

Improving Your Statistical Inferences. Free Coursera course & textbook by Daniel Lakens. Explains what common statistical pitfalls are and techniques for avoiding them.

UC Berkeley Foundations of Data Science. Open source course & textbook by Adhikari, DeNero & Wagner. Combines inferential thinking, computational thinking, and real-world relevance.

Statistical Rethinking. A Bayesian Course with Examples in R and Stan by Richard McElreath. Free YouTube course and textbook. Teaches Bayesian data analysis, but focuses on scientific models first.

SkewTheScript: Free, relevant high school AP math and stats lessons based on real-world problems & data and simulations. Developed by high school teachers for 20,000+ educators.

Data & Science Podcast, by Glen Colopy. Covers critical scientific reasoning from a data science, machine learning, statistics perspective for the practical purpose of becoming a better data scientist.

Teaching Data Science with Scientific Reasoning. Panel with Daniel Lakens, Anthony Fowler, Niki Cotton and Aditya Ranganathan. How to integrate scientific reasoning with teaching data science.

Putting the Science into Data Science. Nov. 14. 2022 Dinner talk by Jay Cordes at Claremont McKenna College, CA. Highlights the importance of a scientific mindset to doing data science (recording & slides).

Centering Data Science Education on Scientific Reasoning. UC Berkeley’s Data Science Education podcast with Julia Koschinsky. “This changes the way we think about teaching data science.”

The 9 Pitfalls of Data Science. Book by Gary Smith & Jay Cordes. Helps guide future data scientists away from the common pitfalls in data science in the corporate world and beyond.

The Phantom Pattern Problem. The Mirage of Big Data. Book by Gary Smith and Jay Cordes. How to avoid the common practice of overdetecting patterns where there are none in the era of big data.

Calling Bullshit. The Art of Skepticism in a Data-Driven World. Book and open course by Bergstrom & West. Questioning existing data and models that count as evidence in social & natural sciences.

Data Colada. Blog by Uri Simonsohn, Leif Nelson and Joe Simmons. Identifying errors and biases in behavioral science research and beyond.

Fooling Ourselves. Nature article by Regina Nuzzo. Humans are remarkably good at self-deception. But reproducibility problems are driving many researchers to seek ways to fight their own worst instincts.

Interactive Simulations for Science and Math (physics, chemistry, math, earth science and biology). Developed by the University of Colorado, funded by the National Science Foundation.

Sense&Sensibility&Science. UC Berkeley Big Ideas course by Saul Perlmutter, John Campbell et al. on the errors humans tend to make, and the approaches science methodology has given us (and we are still developing) to prevent or at least minimize those errors.

On Scientific Method. Lecture by Richard Feynman. “We can never be right, we can only prove we’re wrong.” — “If it disagrees with experiment – it’s WRONG! – That’s all there is to it!”

The Scientific Attitude. Defending Science from Denial, Fraud, and Pseudoscience. Book by Lee McIntyre. An argument that what makes science distinctive is its emphasis on evidence and scientists’ willingness to change theories on the basis of new evidence.

How To Solve It. A System of Thinking to Help You Solve Any Problem. Longtime bestseller by George Polya. How the mathematical method of demonstrating a proof or finding an unknown can be of help in attacking any problem that can be “reasoned” out.

How Not to be Wrong. The Power of Mathematical Thinking. Bestseller by Jordan Ellenberg. Using the mathematical method to understand hidden structures in everyday life. With lots of empirical illustrations.

The Art of Statistics. How to Learn from Data. Book by David Spiegelhalter to establish statistical literacy and guide through key principles we need in order to derive knowledge from data. Based on real-world examples.

5 Techniques of Science Denial. FLICC taxonomy by John Cook et al. Project to help identify and reduce science denial. Includes free course Making Sense of Climate Science Denial.

Error Tight: Exercises for Lab Groups to Prevent Research Mistakes. Tutorial by Julia Strand to help lab groups identify places in their research workflow where errors may occur and how to avoid them.

How to Solve a Mystery Like Sherlock Holmes? Marcos Falcone and Julia Koschinsky compare Sherlock Holmes’ reasoning to Lestrade’s in “The Case of the Six Napoleons” (storymap).

Music to code by from Jay Cordes. Two albums that are great for programming, with a sound that is energetic without being dominating.

Movie: Sherlock Holmes: The Sign of Three. Illustrates reasoning based on a logic of excluding less probable alternatives. Especially scene in ca. 12th-14th minute.

Movie: My Cousin Vinny. Example of effective reasoning, which isn’t taught in school: “Vinnie is terrible at the things we teach and great at the things we don’t teach.”