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
Hypothesis testing is a strange mode for science. You have 3 options: (1) choose as the null something you don't believe; (2) believe that only 1 in 20 of your experiments will produce a "significant" [sic] result; or (3) p-hack. In practice, people choose some combination of 1&3
It's strange, because a really "surprising" paper builds up the null as something people genuinely believe. But - presumably because of some special inside insight - the people involved realized it might be wrong, and so do an experiment to test & reject it.
It's amazing how slowly people are catching on to the flaws of this particular culturally enshrined approach to hypothesis testing. I hope everyone who doesn't already know reads this: https://golem.ph.utexas.edu/category/2010/09/fetishizing_pvalues.html …
Confluence of traditional modes of human storytelling with quantitative science?
There's also the screen + validate approach. First pass test many hypotheses (with some FDR). Then take the ones that pass and do a followup experiment. Now you expect 95% of those to confirm at p = 0.05, and for those to hold up, but some will fully regress to mean.
As a former student I would have loved to express my thoughts that way... but maybe that's also what you're getting at.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
