What's the difference between Statistical versus Practical Significance? If you’re around data at all, you’ve likely heard someone talk about statistical significance. This hurdle is often considered the gold standard in a variety of disciplines for showing that something is true. A new drug being developed needs to show statistically significant efficacy to be considered viable. A new policy intervention is proved effective if it can, with statistical significance, promote a particular behavior. And a choice between different advertisements is made when one statistically significantly outperforms the other on some key metric like favorability.
But even though statistical significance is a minimum requirement for any of those conclusions, it fails to consider something else, meaningful significance. In other words, just because something is true, doesn’t mean it matters all that much. In this episode, if you stick around to the end, I’m going to try and provide an intuitive framework for how to think about whether a result of some kind isn’t just true, but also whether it’s meaningful.
Video explaining statistical significance: https://youtu.be/DAkJhY2zQ3c
Video explaining randomized experiments: https://youtu.be/M1G5MO7JUgI
Learn more about who I am and why I'm doing this here: https://youtu.be/sLIquDwwTpw
Video that has more detail wealth inequality: https://youtu.be/pmW_q5dmosM
Video that explains how to adjust for inflation: https://youtu.be/h2Sb-5E9dt8
Follow me at:
LinkedIn: https://www.linkedin.com/in/jeff-galak-768a193a
Patreon: https://www.patreon.com/datademystified
Equipment Used for Filming:
Nikon D7100: https://amzn.to/320N1FZ
Softlight: https://amzn.to/2ZaXz3o
Yeti Microphone: https://amzn.to/2ZTXznB
iPad for Teleprompter: https://amzn.to/2ZSUkNh
Camtasia for Video Editing: https://amzn.to/2ZRPeAV