I think it’s the same reason I find Numerical Analysis interesting.
How FUN to think about issues that mainly arise when calculating things on computers with finite precision 🤯 e.g. a loss of sparsity when calculating something that analytically, preserves sparsity
(And please NOTE THAT IM SAYING FASCINATING NOT USEFUL-FOR-YOUR-PARTICULAR-APPLICATION 😌)
The most fascinating applications of statistics are the ones where you have to creatively work around pragmatic constraints.
E.g. quasi experimental methods.
A book called “j’apprends a programmer avec python” a French book on programming with python
Mon mari m’a acheté une livre de Python en français pour mon anniversaire.
Bien que je connaisse bien Python…le français…BEAUCOUP mois…😂 alors je vais apprendre rapidement.
* so much respect to those who design it. I feel like stats is not something you can teach well if you are forced to assess via a standardized test (much of which is MCQs)
I’ve been helping a friends kid study for the AP stats exam.
I forgot how much beef I have with the AP Stats curriculum* 😂
A person with a microphone saying “ because I think that something awaits me in the divine for resisting“
Them: why do you keep calling yourself a “statistician” instead of a “data scientist”
Me:
Unfortunately all my data is shited 😔
My query just failed to run because I referenced a CTE as “unshited” 💩 instead of “unshifted” so…
Me looking annoyed
Yeah my face is stuck like this now😔
We LOVE DATA ENGINEERS 🙇🏻♀️
My corgi nova looking suspicious
Me when I can’t SELECT * FROM AMAZING_DATA.CLEAN_TABLE
Santa climbs in a window, sees a letter written to him from a small child who is sleeping. The letter reads “observe the counter factual”. After reading this Santa tries to shoot the child.
🎅
I actually don’t mind “there’s a 95% chance this kind of interval contains….”🤔
💀
that does not meaningfully improve people’s ability to live and work with CIs 🫨 I’ve had every opinion about CIs under the sun, but this is the most peace I have felt about them 🧘♀️🧘♀️🧘♀️
Mattan…I cannot do it anymore 🧘♀️I’m sick of wasting my time with a technically correct but practically meaningless interpretation of CIs. We’re confusing people with the “95% confident” language in order to eke out a tiny bit more technical accuracy
above, perhaps a bit Bayesian?) to say there’s a 95% chance my interval contains mu
- while technically the prob is 0/1 I can’t actually observe that, so I rely on my knowledge that under blah blah assumptions, in the long run, 95% of the confidence intervals constructed in this way contain mu. So without further knowledge about MY interval, I think it’s fine (though I admitted
Why is it wrong (I’m not asking because I think it’s perfectly, technically correct, but because I think the reason people say it’s incorrect doesn’t really matter)
- The statement reflects the idea that frequentists view the sample as random (and therefore the interval) not the parameter
95% confident is just a way to be technically correct by being unclear
Just say there’s a 95% chance my interval contains the pop mean.
(It’s better than saying there’s a 95% chance the pop mean is in my interval. I cant do the whole “it’s either 0 or 1” thing. Im embracing the bayesian probability interpretation)
And honestly what the fuck does that even MEAN?! Nothing.
Drilling students into memorizing the “we are 95% confident that….” Language is USELESS if you dont teach them what that MEANS
Just saw that @aclu.org is suing over this!
action.aclu.org/give/pm-dona...
Ugh I want that to be true 😭 I hope it is true, but I’m fearful it’s not
It’s the literal least anyone can do 😭
- real sus that you want to require specific ID to vote and then immediately set precedent to instantaneously invalidate people’s ids
- this also includes a “bounty” on trans people using the bathroom. Which is so disgusting I cannot even express how bad of an idea this is
This is deeply alarming.
