my favorite erroneous data/outlier story:

uncle was running a study on fish and had students helping note down behavioral data. everyone& #39;s collecting data, it all looks pretty consistent, all good.
ONE student is getting really bizarre outlier data though. what& #39;s going on? they observe HER observing THE FISH and realize that the fish actually ARE behaving differently when she& #39;s taking the readings.
turns out: because she& #39;s the shortest in the group, she& #39;s the only one the fish don& #39;t all immediately notice when she comes in to take readings on them in their tank. everybody else is taking readings on stressed out fish, she& #39;s taking readings on undisturbed fish.
there are a ton of important lessons. i mostly just think it& #39;s really funny how bad we are at this stuff though.
You can follow @JoINrbs.
Tip: mention @twtextapp on a Twitter thread with the keyword “unroll” to get a link to it.

Latest Threads Unrolled: