Chelsea Parlett
@ChelseaParlett
Followers
37K
Following
63K
Media
8K
Statuses
34K
📊Statistician, 👩🏻🏫Data Science Prof, ✍️Stats Communication. #statistics #scicomm #datascience #statstiktok 👩🏻💻 she/her
who’s to say?
Joined October 2011
RT @ChelseaParlett: There once was a model, ANOVA,.who along with their cousin ANCOVA,.made a great big confession:.“We’re the same as regr….
0
554
0
RT @JohnHolbein1: What are some of the unwritten rules of the academe? . [Motivation: I recently spoke with a grad student who expressed b….
0
18
0
RT @sirbayes: I am pleased to announce a new version of my RL tutorial. Major update to the LLM chapter (eg DPO, GRPO, thinking), minor upd….
0
452
0
*taps the sign*
A famous person wore a secret hidden wire while speaking with me about AI, and I want to talk about it. Backstage at a recent AI event, I was talking with someone about private views on AI investments and strategy. We were both unfiltered. At one point, I joked, “We should’ve.
0
1
7
If you want to support local bookstores but also love audio books @librofm is having a sale today 🥳. I picked up a few books on my to-read list like Piranesi, and The House in the Cerulean Sea for ~ $5 each 😱. 📚
libro.fm
Libro.fm makes it possible for you to buy audiobooks directly through local bookstores.
0
0
2
If you don’t incentivize good code hygiene, organization, and documentation (through recognition, and KPIs), people are not going to do it, and everyone will suffer.
3
3
33
RT @MatthewBJane: Error Report #4: The meta-analysis on Fluoride and IQ by Taylor et al. (2025) is methodologicall….
0
31
0
RT @SashaMTL: Check out the cool demo @juliendelavande made in honor of Earth Day! 💚.Check it out to see estimates of how much ⚡ energy⚡ yo….
0
4
0
3. it makes "non-significant" tests easier to use well (e.g. "yes CEO the effect was precisely estimated to be practically equivalent to 0").
0
0
6
1. it makes the "we should throw out results from non significant tests" fallacy less salient. 2. it highlights the need to incorporate uncertainty into your decision making (more precise estimate, more confident forecasts/predictions).
1
0
4
powering for precision of your estimate is *very often* more useful than powering for statistical significance. I often run into marketing incrementality testing recommendations that base recommendations on statistical power, but precision is a better way to frame this.
2
4
37
Got new posters for the office! . One for my life’s obsession (math/stats) and one for Tony’s (public transportation) . AND THEIR COLOR PALETTES MATCH🥳 . @streetsforall @DFTBArecords
0
0
6
RT @nickchk: The second edition of The Effect is now available for preorder! This version has a whole new chapter on Partial Identification….
routledge.com
The Effect: An Introduction to Research Design and Causality, Second edition is an excellent teaching text about research design, specifically concerning research that uses observational data to make...
0
73
0
If anyone can make Quaternions feel intuitive it's @3blue1brown and @ben_eater 👑. There's always been something. fuzzy to me about how quaternions work (probably that pesky 4th dimension. ) and this is the best intuition building explainer I've seen.
0
0
3
If you see the Greek letter ξ, you’re in for a bad time.
2
1
26
I think there’s a lot to be said about geometric interpretations and explanations of statistics.
4
0
17