So, several people pointed out that this table is very weird, and I agree It's hard to see how these values are ~possible~, given the p-value beneathhttps://twitter.com/GidMK/status/1213944606510866432 …
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Ideally try something other than the uniform for your random numbers ...
Looking at the quartiles, it should be symmetric
I think you’ll still get a similar result
Ok, I like a good puzzle. Tackling from a different angle, with the p-value we know that z = 2.29 for the Wilcox Sign-Rank test. Formula is straightforward (attached). So you can reverse engineer the sum of rank differences to be ~2647: https://docs.google.com/spreadsheets/d/1AnrNa1wRcZwnYIJZZWJKTvAr6Xb8bLUPriJwkSTj46A/edit?folder=0AB0NnJUw_mIsUk9PVA#gid=0 …pic.twitter.com/dvk4v9veck
I'm not so good a coder though, so after that I'm not sure if that's a plausible value given the other parameters. I wonder if that might help with a simulation though? I tried SPRITE on the means, but seemingly plausible.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.