Dark Data: Why what you don’t know matters
The Effective Statistician - in association with PSI
00:00
Covid and Dark Data
Covid and dark data is a special problem in that sort of medical and pharmasectra, exactly as you say. So much of it is observational, not controlled. The doctor chooses one because they have experience of it in the past and think it will do better. One way to cope with dark data is to understand why you've got dark data and what we might be missing. And then how do i compensate for this? How do I cover up for it and covertly change my analysis? That's right! You can't hide from your biases any more than you can hide from your own prejudices or blind spots. We're talking about very little coatit, adjustment at
Transcript
Play full episode
