Chelsea Parlett
@chelseaparlett.bsky.social
Ph.D, stats lover/writer✍🏼, #statistics #scicomm #datascience #statstiktok 👩🏻💻 she/her
Braiding Sweetgrass (paraphrasing): no one becomes a scientist because of the wonder of data or p-values
Me: ☝️ not NO one…👀
Me: ☝️ not NO one…👀
November 26, 2025 at 3:28 AM
Braiding Sweetgrass (paraphrasing): no one becomes a scientist because of the wonder of data or p-values
Me: ☝️ not NO one…👀
Me: ☝️ not NO one…👀
Oh no I have a query that will take ~7 minutes to run, I can’t possibly do anything productive during that small amount time, I better go scroll on social media…!
a cartoon of grinch with a very angry look on his face
ALT: a cartoon of grinch with a very angry look on his face
media.tenor.com
November 24, 2025 at 1:17 AM
Oh no I have a query that will take ~7 minutes to run, I can’t possibly do anything productive during that small amount time, I better go scroll on social media…!
what are those ✨nostalgic✨ textbooks for you? not the most useful textbooks, or the ones you liked the most, but the ones that really take you back...
for me, Strang's Linear Algebra and Casella + Berger's Statistical Inference come to mind
for me, Strang's Linear Algebra and Casella + Berger's Statistical Inference come to mind
November 23, 2025 at 1:54 AM
what are those ✨nostalgic✨ textbooks for you? not the most useful textbooks, or the ones you liked the most, but the ones that really take you back...
for me, Strang's Linear Algebra and Casella + Berger's Statistical Inference come to mind
for me, Strang's Linear Algebra and Casella + Berger's Statistical Inference come to mind
That’s why we have strongly informative priors amirite? /s
Sometimes people just want numbers that tell them to do what they already want to do 🤷♀️
November 22, 2025 at 1:48 AM
That’s why we have strongly informative priors amirite? /s
Sometimes people just want numbers that tell them to do what they already want to do 🤷♀️
November 21, 2025 at 9:20 PM
Sometimes people just want numbers that tell them to do what they already want to do 🤷♀️
IF YOURE NOT GOING TO LOOK AT THE UNCERTAINTY OF YOUR ESTIMATES WHY BOTHER DOING THE ANALYSIS AT ALL
#pikasShoutStats
#pikasShoutStats
November 21, 2025 at 8:50 PM
IF YOURE NOT GOING TO LOOK AT THE UNCERTAINTY OF YOUR ESTIMATES WHY BOTHER DOING THE ANALYSIS AT ALL
#pikasShoutStats
#pikasShoutStats
She doesn’t even know about the assumption of homoskedasticity 🥹
November 19, 2025 at 8:16 PM
She doesn’t even know about the assumption of homoskedasticity 🥹
The people yearn for adorable math slides
November 17, 2025 at 9:54 PM
The people yearn for adorable math slides
Me: *unsuccessfully tries zero-shot learning*
Me to my LLM:
Me to my LLM:
November 17, 2025 at 5:01 AM
Me: *unsuccessfully tries zero-shot learning*
Me to my LLM:
Me to my LLM:
THAT INCREASE IN PRECISION OF YOUR ESTIMATE COMES AT THE COST OF MORE ASSUMPTIONS AND/OR OUTSIDE INFORMATION.
MAKE SURE THOSE ASSUMPTIONS ARE GOOD!!!
#pikasShoutStats
MAKE SURE THOSE ASSUMPTIONS ARE GOOD!!!
#pikasShoutStats
a small animal is yawning on a rock
Alt: a small pika is shouting on a rock
media.tenor.com
November 17, 2025 at 4:30 AM
THAT INCREASE IN PRECISION OF YOUR ESTIMATE COMES AT THE COST OF MORE ASSUMPTIONS AND/OR OUTSIDE INFORMATION.
MAKE SURE THOSE ASSUMPTIONS ARE GOOD!!!
#pikasShoutStats
MAKE SURE THOSE ASSUMPTIONS ARE GOOD!!!
#pikasShoutStats
Just because an LLM can give you an output that’s not immediately and obviously wrong doesn’t mean it is a USEFUL or correct output
I think we need to spend a LOT more time thinking about whether the lack of trust/verification of these outputs is a dealbreaker
(I’d guess…it is)
I think we need to spend a LOT more time thinking about whether the lack of trust/verification of these outputs is a dealbreaker
(I’d guess…it is)
a man in a white shirt is standing in front of a pink fence
ALT: a man in a white shirt is standing in front of a pink fence
media.tenor.com
November 17, 2025 at 4:27 AM
Just because an LLM can give you an output that’s not immediately and obviously wrong doesn’t mean it is a USEFUL or correct output
I think we need to spend a LOT more time thinking about whether the lack of trust/verification of these outputs is a dealbreaker
(I’d guess…it is)
I think we need to spend a LOT more time thinking about whether the lack of trust/verification of these outputs is a dealbreaker
(I’d guess…it is)
There’s something really powerful about justifiable approximations 😍
Being in industry for a bit, I’m really learning to love the process of “right-sizing” analyses and providing emperical support for any approximations/simplifications that are needed.
Being in industry for a bit, I’m really learning to love the process of “right-sizing” analyses and providing emperical support for any approximations/simplifications that are needed.
November 16, 2025 at 7:10 PM
There’s something really powerful about justifiable approximations 😍
Being in industry for a bit, I’m really learning to love the process of “right-sizing” analyses and providing emperical support for any approximations/simplifications that are needed.
Being in industry for a bit, I’m really learning to love the process of “right-sizing” analyses and providing emperical support for any approximations/simplifications that are needed.
In another life I would have liked to study topology. Or library sciences.
November 16, 2025 at 7:04 PM
In another life I would have liked to study topology. Or library sciences.
I love a good math problem
a little girl is laughing with her fist in the air while wearing a vest and tie .
ALT: a little girl is laughing with her fist in the air while wearing a vest and tie .
media.tenor.com
November 14, 2025 at 8:26 PM
I love a good math problem
New Data Scientists when they find out their job is mostly dashboarding and data engineering
November 14, 2025 at 8:25 PM
New Data Scientists when they find out their job is mostly dashboarding and data engineering
ChatGPT sassing me for asking questions 🙂↔️💀
November 12, 2025 at 10:38 PM
ChatGPT sassing me for asking questions 🙂↔️💀
Revisiting @phdemetri.bsky.social’s “What is Confounding?” blog this morning.
What a great way to:
1: help people understand what confounding is doing and
2: show why randomization gets rid of a lot of causal worries for you!
🔗: dpananos.github.io/posts/2024-0...
What a great way to:
1: help people understand what confounding is doing and
2: show why randomization gets rid of a lot of causal worries for you!
🔗: dpananos.github.io/posts/2024-0...
Demetri Pananos Ph.D - What Is Confounding?
dpananos.github.io
November 10, 2025 at 7:23 PM
Revisiting @phdemetri.bsky.social’s “What is Confounding?” blog this morning.
What a great way to:
1: help people understand what confounding is doing and
2: show why randomization gets rid of a lot of causal worries for you!
🔗: dpananos.github.io/posts/2024-0...
What a great way to:
1: help people understand what confounding is doing and
2: show why randomization gets rid of a lot of causal worries for you!
🔗: dpananos.github.io/posts/2024-0...
Noooo don’t overfit your so sexy hahah
November 9, 2025 at 5:28 AM
Noooo don’t overfit your so sexy hahah
I love nothing more than when my coworkers’ dogs walk in frame during a zoom meeting 🥹
November 7, 2025 at 6:58 PM
I love nothing more than when my coworkers’ dogs walk in frame during a zoom meeting 🥹
“look how much better my favorite model is compared compared to these other TRASH MODELS😒😒😒 when I specifically chose a DGP that matches my models assumptions and not the others’😌”
November 7, 2025 at 4:13 AM
“look how much better my favorite model is compared compared to these other TRASH MODELS😒😒😒 when I specifically chose a DGP that matches my models assumptions and not the others’😌”
LET HIM COOK
Do you teach #rstats? Do your students complain about how lame and old-fashioned dplyr is? Don't worry: I have the solution for you: github.com/hadley/genzp....
genzplyr is dplyr, but bussin fr fr no cap.
genzplyr is dplyr, but bussin fr fr no cap.
GitHub - hadley/genzplyr: dplyr but make it bussin fr fr no cap
dplyr but make it bussin fr fr no cap. Contribute to hadley/genzplyr development by creating an account on GitHub.
github.com
November 7, 2025 at 4:05 AM
LET HIM COOK
If no one values you spending time on documentation, just tell them you’re making a Chatbot and you’re building content for RAG
a close up of a man 's face with a shaved line on his head .
ALT: a close up of a man 's face with a shaved line on his head .
media.tenor.com
November 6, 2025 at 5:11 AM
If no one values you spending time on documentation, just tell them you’re making a Chatbot and you’re building content for RAG
