John Muschelli
@strictlystat.bsky.social
Associate Research Professor at https://bsky.app/profile/jhubiostat.bsky.social. Trying not to drown in the sea of data. Tweets are my own. Random Blog stuff at https://hopstat.wordpress.com/
Reposted by John Muschelli
Jobs with biggest % decline in job postings include lots of creative jobs. And *biostatisticians* 😬
These are thought to be most impacted by AI. Great job everyone.
bloomberry.com/blog/i-analy...
These are thought to be most impacted by AI. Great job everyone.
bloomberry.com/blog/i-analy...
November 14, 2025 at 7:35 AM
Jobs with biggest % decline in job postings include lots of creative jobs. And *biostatisticians* 😬
These are thought to be most impacted by AI. Great job everyone.
bloomberry.com/blog/i-analy...
These are thought to be most impacted by AI. Great job everyone.
bloomberry.com/blog/i-analy...
“There’s more open imaging data about listening to music than menopause and contraceptives effect on the brain” #nexus @russpoldrack.org
November 14, 2025 at 4:06 PM
“There’s more open imaging data about listening to music than menopause and contraceptives effect on the brain” #nexus @russpoldrack.org
Reposted by John Muschelli
Trump has only ever really cared about one issue: Email storage.
November 13, 2025 at 1:11 AM
Trump has only ever really cared about one issue: Email storage.
Reposted by John Muschelli
Best case: The President of the United States knew about a pedophilia ring and did nothing to stop it.
Medium case: He also used his office to protect the perpetrators.
Worst case: Because he was one of the perpetrators.
Medium case: He also used his office to protect the perpetrators.
Worst case: Because he was one of the perpetrators.
November 13, 2025 at 2:39 AM
Best case: The President of the United States knew about a pedophilia ring and did nothing to stop it.
Medium case: He also used his office to protect the perpetrators.
Worst case: Because he was one of the perpetrators.
Medium case: He also used his office to protect the perpetrators.
Worst case: Because he was one of the perpetrators.
Reposted by John Muschelli
This is one of the most remarkable academic debacles I've ever seen.
A large RCT got published in BMJ. There are currently 44 Pubpeer comments, mostly about the data, including...well. Read for yourself.
pubpeer.com/publications...
A large RCT got published in BMJ. There are currently 44 Pubpeer comments, mostly about the data, including...well. Read for yourself.
pubpeer.com/publications...
PubPeer - Prevention of acute myocardial infarction induced heart fail...
There are comments on PubPeer for publication: Prevention of acute myocardial infarction induced heart failure by intracoronary infusion of mesenchymal stem cells: phase 3 randomised clinical trial (P...
pubpeer.com
November 11, 2025 at 1:19 AM
This is one of the most remarkable academic debacles I've ever seen.
A large RCT got published in BMJ. There are currently 44 Pubpeer comments, mostly about the data, including...well. Read for yourself.
pubpeer.com/publications...
A large RCT got published in BMJ. There are currently 44 Pubpeer comments, mostly about the data, including...well. Read for yourself.
pubpeer.com/publications...
I used to feel some type of way when people would write `library(tidyverse)` in #rstats scripts. I've written a lot of packages so it seems like a dependency hell (which it is for pkgs). Although introduces many dependencies for the script, I've come around to making scripts quick to make.
October 24, 2025 at 7:39 PM
I used to feel some type of way when people would write `library(tidyverse)` in #rstats scripts. I've written a lot of packages so it seems like a dependency hell (which it is for pkgs). Although introduces many dependencies for the script, I've come around to making scripts quick to make.
Reposted by John Muschelli
My NIH study section will not meet tomorrow because of the government shutdown. This may seem trivial but rescheduling these meetings will delay funding decisions for months to even a year! Let alone the uncertainty of what the FY26 budget will be. Awful for US scientists! 😓
October 22, 2025 at 10:31 PM
My NIH study section will not meet tomorrow because of the government shutdown. This may seem trivial but rescheduling these meetings will delay funding decisions for months to even a year! Let alone the uncertainty of what the FY26 budget will be. Awful for US scientists! 😓
Soft money environment: grants don’t care about sick days
October 22, 2025 at 3:59 PM
Soft money environment: grants don’t care about sick days
Reposted by John Muschelli
One of the conversations I've been trying to have with anyone who will listen if that for unis like mine, which have big classes, this will require either shrinking class sizes drastically or significantly scaling up teaching assistance. There's no way around it.
go, student newspaper of Notre Dame and Saint Mary
"employ in-class essays, oral exams+ rigorous discussions — that are far more difficult to use AI tools to complete. a close reading of the text should constitute the bulk in any introductory humanities class."
www.ndsmcobserver.com/article/2025...
"employ in-class essays, oral exams+ rigorous discussions — that are far more difficult to use AI tools to complete. a close reading of the text should constitute the bulk in any introductory humanities class."
www.ndsmcobserver.com/article/2025...
Editorial: AI-proof the Core Curriculum
The Core Curriculum is an essential part of a Catholic education that must be saved from AI.
www.ndsmcobserver.com
October 20, 2025 at 3:28 AM
One of the conversations I've been trying to have with anyone who will listen if that for unis like mine, which have big classes, this will require either shrinking class sizes drastically or significantly scaling up teaching assistance. There's no way around it.
Does editorial manager work with any password manager? Or is it either I change email for each journal (with + tag) or I have just one password for all reviewing/authorship?
October 15, 2025 at 2:52 PM
Does editorial manager work with any password manager? Or is it either I change email for each journal (with + tag) or I have just one password for all reviewing/authorship?
Reposted by John Muschelli
probably my most deeply-held belief: it is not possible for a slide deck to be both (1) a good presentation aide; and (2) a standalone document that can be read and understood in isolation.
October 14, 2025 at 8:08 AM
probably my most deeply-held belief: it is not possible for a slide deck to be both (1) a good presentation aide; and (2) a standalone document that can be read and understood in isolation.
A software story: Positron rolled out AI test features (don’t think assistant was live) in release. Users 🤔. Posit - whoops logic failed - need more conditions, PR. Fin.
October 13, 2025 at 4:04 AM
A software story: Positron rolled out AI test features (don’t think assistant was live) in release. Users 🤔. Posit - whoops logic failed - need more conditions, PR. Fin.
Reposted by John Muschelli
October 12, 2025 at 1:23 PM
Reposted by John Muschelli
Okay, I opened an issue to discuss adding hierarchical code folding to RStudio!
github.com/rstudio/rstu...
If you want to try it out yourself (and don't mind waiting walking away from your computer for a long time while boost compiles), try out the branch here:
github.com/tylermorganw...
#Rstats
github.com/rstudio/rstu...
If you want to try it out yourself (and don't mind waiting walking away from your computer for a long time while boost compiles), try out the branch here:
github.com/tylermorganw...
#Rstats
October 13, 2025 at 12:31 AM
Okay, I opened an issue to discuss adding hierarchical code folding to RStudio!
github.com/rstudio/rstu...
If you want to try it out yourself (and don't mind waiting walking away from your computer for a long time while boost compiles), try out the branch here:
github.com/tylermorganw...
#Rstats
github.com/rstudio/rstu...
If you want to try it out yourself (and don't mind waiting walking away from your computer for a long time while boost compiles), try out the branch here:
github.com/tylermorganw...
#Rstats
Reposted by John Muschelli
"You have enslaved him. You have placed Fester under some strange sexual spell. I respect that. But please… You have gone too far. You have married Fester, you have destroyed his spirit, you have taken him from us. All that I could forgive. But, Debbie…pastels?"
October 13, 2025 at 1:04 AM
"You have enslaved him. You have placed Fester under some strange sexual spell. I respect that. But please… You have gone too far. You have married Fester, you have destroyed his spirit, you have taken him from us. All that I could forgive. But, Debbie…pastels?"
www.nature.com/articles/d41... is discussing a surge in papers that likely use LLMs on open data. This is concerning since I work on one of those sets (NHANES) and this may be when the pendulum swings against fully public data sets since that data may then be used to churn out low quality papers.
Low-quality papers based on public health data are flooding the scientific literature
The appearance of thousands of formulaic biomedical studies has been linked to the rise of text-generating AI tools.
www.nature.com
October 10, 2025 at 12:29 PM
www.nature.com/articles/d41... is discussing a surge in papers that likely use LLMs on open data. This is concerning since I work on one of those sets (NHANES) and this may be when the pendulum swings against fully public data sets since that data may then be used to churn out low quality papers.
Reposted by John Muschelli
Amazing how much the fascists hate and target anyone associated with anti-fascism in any way, and then at the same time claim that they are not fascists. 🤷♂️
October 9, 2025 at 4:14 PM
Amazing how much the fascists hate and target anyone associated with anti-fascism in any way, and then at the same time claim that they are not fascists. 🤷♂️
Reposted by John Muschelli
Seems like this works?
October 9, 2025 at 3:05 PM
Seems like this works?
Reposted by John Muschelli
I’ve been an Apple fanboy for 15 years and even I find this shameful and disgusting
New: Apple banned an app that simply archived videos of ICE abuses. Rather than other apps that record ICE official's real-time location, Eyes Up is to "preserve evidence until it can be used in court." Videos from TikTok etc. Every submission manually reviewed
www.404media.co/apple-banned...
www.404media.co/apple-banned...
Apple Banned an App That Simply Archived Videos of ICE Abuses
Eyes Up's purpose is to "preserve evidence until it can be used in court." But it has been swept up in Apple's crackdown on ICE-spotting apps.
www.404media.co
October 8, 2025 at 9:17 PM
I’ve been an Apple fanboy for 15 years and even I find this shameful and disgusting
Reposted by John Muschelli
This is important.
Today my @nytimes.com colleagues and I are launching a new series called Lost Science. We interview US scientists who can no longer discover something new about our world, thanks to this year‘s cuts. Here is my first interview with a scientist who studied bees and fires. Gift link: nyti.ms/3IWXbiE
nyti.ms
October 9, 2025 at 2:52 AM
This is important.
Reposted by John Muschelli
I see pieces like this a lot, often w/ a spin of lamenting cultural degeneration, but reading is a LABOR issue, it’s declined because so many people are working overtime or two jobs & employers expect after hours work. France has Earth’s highest reading rate b/c long lunch breaks & labor protections
October 7, 2025 at 12:25 AM
I see pieces like this a lot, often w/ a spin of lamenting cultural degeneration, but reading is a LABOR issue, it’s declined because so many people are working overtime or two jobs & employers expect after hours work. France has Earth’s highest reading rate b/c long lunch breaks & labor protections