Advik Shreekumar (@AdvikSh) header
Advik Shreekumar (@AdvikSh) profile picture

PhD student @MITEcon «- @UChiUrbanLabs «- @CivisAnalytics Late PhD potpourri: behavioral + methods. Putting the yo in RStudio.

Boston, MA
Joined June 2009
Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)Photo by Advik Shreekumar (@AdvikSh)
"A Night of Second-Year Research" (Google searches on canvas, artist unknown)
2
51
Stay tuned for my eventual tirade on the lasso in econ. It's a cool tool! But I'd bet: 1) We'd be way more critical of lasso stated as a Laplace prior on coefficients. 2) Cross-validation is secretly doing a lot of work. 3) Lasso's popular because GBTs aren't in Stata.
This Post is from an account that no longer exists. Learn more
1
595
I’m thrilled to announce Conformal Risk Control: a way to bound quantities other than coverage with conformal prediction. arxiv.org/abs/2208.02814 Check out the worked examples in CV and NLP! The best part is: it’s exactly the same algorithm as split conformal prediction🤯🧵1/5
2
29
6
139
Retweeting b/c I want to test two hypotheses based on regression: 1) Is A less sensitive to treatment than B? H0: |b1| < |b2| 2) Does treatment push A and B the same way? H0: sign(b1) = sign(b3) I'm frustrated b/c this is hard with my econ toolkit, but easy with Bayes. (1/n)
Apparently there was a series of Bayesian statistics conferences in Spain starting in the late 1970s, and they had a tradition of cabaret songs about how great Bayes' theorem is
1
2
I appreciate that econ tries to make few assumptions in regression*. But it's not costless! Makes it hard to answer questions like: — Is A less sensitive to treatment than B? — Does treatment push A and B the same way? * the assumptions get shifted to the asymptotics. (n/n)
1
(yes this thread is both a complaint and a cry for help)
Here's a 1-minute video showing--in the words of visualization hero @EdwardTufte--the "compared to what" factor for today's amazing @NASAWebb image. Thanks to the @WWTelescope for making this possible, and @ADavidWeigel. I only wish @NASA and @POTUS had shown the image this way!
271
5,921
2,170
17,126
Finally figured out a way to lose a bunch of followers. For tweets like this: ≻≻>
Finally figured out a way to lose a bunch of followers: cantaloupe > mango
1
NEW PREPRINT The increasingly popular class imbalance approaches (such as SMOTE) for risk prediction modeling: they are likely to do more harm than good arxiv.org/abs/2202.09101
14
106
35
452
Wordle's been a fun reminder of how many fantastic 5-letter words we have: angst, thyme, inure, grist, haunt, spurn, glyph, psalm, foist ... I love how they look, feel to say, evoke so much despite being short. Any crowd favorites?
1
9
Another easy fixed is one extra quarter and a jump ball?
One issue with this is that it's still a pretty big advantage to get the ball first, so you could play two 7:30 (or 5:00) periods instead.
This has gone too far
13
I may be the first person in human history to dip a Totino's Pizza Roll™ in inji thayir.
5
This but for getting really good at Tableau
Not gonna lie... think twice before you become the guy who can debug all the layers of the stack. You won't make more money and you'll probably work way longer hours :(
1
2
To my fellow young researchers: learn from the past. Use leave-one-out cross-validation.
Important point. Young researchers have mostly missed out on the opportunities we had back in the 1980s and 1990s to start a program running and then claim to be "working" for days on end while it ran. #multitasking
5
I'm a monster for tweeting the punchline and not the whole thread, but this is a helluva punchline.
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more