Photo by Simon Rae on Unsplash

The Zen of Data

Inspired by The Zen of Python

• More data is better than less data.
• Correct data is better than incorrect data.
• Ethically gathered data is better than unethically gathered data.
• Explicit assumptions are better than implicit ones.
• Explaining predictions is desirable whenever possible.
• Correlation does not imply causation. Really.
• Randomized controlled experiment (RCE) is the gold standard for proving causality.
• In some observational datasets causal inference *can* still be achieved even without RCE.
• All else being equal the simpler model is better.
• A good model using bad data is a bad model.
• False Positives and False Negatives do not always have the same weight.
• Visualizations should not sacrifice information content and readability for cleverness or novelty.