oh gosh I am glad they included scatterplots but gosh https://twitter.com/NicoleBarbaro/status/1134103469533618176 …
-
This Tweet is unavailable.Show this thread
-
-
Replying to @eigenrobot
what’s going on here i don’t stats can you realy just arbitrarily pick dots and draw a line through them how do you pick the dots
1 reply 1 retweet 3 likes -
Replying to @moon_of_a_moon
wellll new evidence suggest that in fact you can do that
1 reply 0 retweets 12 likes -
Replying to @eigenrobot
stats is so confusing the rules all seem so arbitrary i know there’s a rationale behind them but i’ve never taken a stats class that wasn’t “just learn the rules and then apply them stop asking why the rule exists” so it always seems a little like spooky magic to me
1 reply 0 retweets 3 likes -
Replying to @moon_of_a_moon
yeah it took me maybe a solid eight years of constant coursework and fucking up before I figured out what was going on
1 reply 0 retweets 5 likes -
Replying to @eigenrobot
philemon Retweeted philemon
Any way to condense some lessons learned out of those eight years or is it one of of those things you kind of just have to grind through and learn the hard way?https://twitter.com/phil49472744/status/1215045861505470465 …
philemon added,
1 reply 0 retweets 2 likes
Hmm Honestly perhaps something like: 1. Learn frequentist statistics for experiments but with bootstrap standard errors 2. Learn the basic ML paradigm, focus less on model classes and more on conceptual framework 3. Read Mostly Harmless Econometrics for an intro to causality
-
-
Replying to @eigenrobot @phil49472744
Or perhaps take
@nickchk's course he's got a killer approach to this1 reply 0 retweets 3 likes -
eigenrobot Retweeted Nick HK
eigenrobot added,
1 reply 0 retweets 3 likes - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.