Profile avatar
neurostats.org
AI in Bio & Health & Therapeutic Development Bio: https://linktr.ee/mnarayan Substack: https://blog.neurostats.org Peek into my brain: notes.manjarinarayan.org Previously @dynotx @StanfordMed PhD@RiceU_ECE | BS@ECEILLINOIS 🧪🧮⚕️🧬🧠🖥🤖📈✍️🩺👩‍📈📉
1,404 posts 7,098 followers 810 following
Regular Contributor
Active Commenter
Posts 15 Comments 35

Describing a series of correlations as proof of mediation is one of the most heinous epistemic crimes.

submitted 16 hours ago • 2 comments

Cui bono? What the elimination of NSF grants focused on understanding and preventing science misinformation affects, by the former director of the NSF Science of Science program. 🧪 #academicsky

submitted 2 days ago • 0 comments

Oof. I dug into a lot of stroke therapeutics research last year and it was never clear what the quality of preclinical evidence was.

submitted 2 days ago • 0 comments

Banning synthetic food dyes won’t improve health—it may worsen it. FOOD DYES AREN’T THE ISSUE. 1️⃣ they’re safe at ingested levels. 2️⃣ they’re not banned in other countries. 3️⃣ they’ll be replaced with other dyes that aren’t safer, as stable, or as studied. 1/

submitted 2 days ago • 22 comments

Please consider making a public comment opposing the possibility of making NIH directors, program officers, and other staff (e.g. SRO, GMS) political appointees. This only took me ~90 seconds. Please repost. Thanks 👍

submitted 2 days ago • 1 comment

"This allows for many civil service positions to be replaced with political appointees. This could include NIH institute directors and even POs." Call to action: Send comments

submitted 2 days ago • 0 comments

#statsmeme

submitted 4 days ago • 1 comment

Looks interesting and relevant to the issue of LLMs interpreting science papers given p-values. This is an open ended question and the vast majority of the scientific literature doesn't interpret them correctly. Just think of all the 'trends toward significance' phrases out there.

submitted 4 days ago • 0 comments

There are a lot of folks with good philosophical instincts outside the profession. In fact scientists and scholars who think deeply often channel original phil.sci or phil ethics views. But this feels so inclusive as to be eliminativist about what philosophy is.

submitted 4 days ago • 0 comments

I've had to reference Daniel Carpenter's book so often I just finally got a physical copy.

submitted 4 days ago • 0 comments

Also, I'm going to need to see some polling about what Middle America thinks before I take a strong position on ICE detaining U.S. citizens for 10 days for not showing papers. news.azpm.org/p/news-artic...

submitted 5 days ago • 18 comments

I called this a few weeks ago. It's up to individual scientists and universities involved in collecting that data to do what is needed here.

submitted 7 days ago • 0 comments

🧪

submitted 7 days ago • 0 comments

It struck a chord because it's true. As I write in More Than Words, the chief benefit of LLMs to writing (and teaching writing) is it forces us to examine what we value in writing. We should be building statues of the students who remain proud to be themselves & encourage others to join them.

submitted 8 days ago • 4 comments

I occasionally delude myself that I know something about stats. Today I learned a word from my 6 year old granddaughter: “subitising”. I told her she must mean “summarising”. Now that she’s asleep I have looked it up. Apologies will be due at breakfast.

submitted 8 days ago • 2 comments