Bulat Zagidullin

paraphrasing one of the greats: it's already there, just chisel away the unnecessary bits

@affineincontrol nor can you use scientific method to answer things like "is the water wet" or "is my red the same as your red"

@b_zagidullin Easiest is the most general "how does A affect B when C, D, E, F, G are held fixed at specific values" Knowing the vast empirical literature on in-animal deep brain stimulation doesn't readily tell you the info you need for real world patients whete C-G can't be fixed.

In today's academic ecosystem, the folks considered most expert are also the most narrow. It's rare that they're ever wrong about their answer, but it's clear they're almost always wrong about the question they think they need to answer.

@_fernando_rosas @rlmcelreath @philipcball here is a great talk by J Crutchfield from a couple years ago, where he talks about e-machines, emergence and demonology youtu.be/gwbq2MJBnWw?si… (better quality link in comments) may be worth checking out if anyone is interested to learn more about the topic great article!

Great piece about emergence covering our recent work, beautifully written by @philipcball 👇🏽👇🏽👇🏽

@JoachimSchork any idea how to detect Simpson's paradox in large p small n scenario? I find that it is reasonable to manually check for it when there are tens of variables, but it becomes nigh impossible when there are 100s-1000s

Simpson’s Paradox is a fascinating statistical phenomenon where the relationship between two variables can completely change when a third variable is considered. This often leads to contradictory conclusions if not carefully analyzed. For example, in a data set, you might see a positive trend between variables X and Y. However, when you split the data into subgroups based on a third variable, Z, the trend might reverse or disappear. Key takeaways: ✔️ Always consider potential lurking variables that could influence your results. ✔️ Be cautious with aggregated data; sometimes the real insights lie in the subgroups. ✔️ Use visualizations to better understand the relationships within your data. Giannis Tolios shared this great visualization on Simpson's Paradox in a recent post, emphasizing the importance of thorough analysis to avoid such pitfalls. This paradox underscores the necessity for data analysts to be meticulous in their work to prevent erroneous interpretations. #statistics #datascience #statisticalanalysis

@drmichaellevin @DougBlackiston @csgrasso10 @ThosVarley @spornslab @DoctorJosh @Sara_Imari oh wow, neat work, both experiments and data analysis are rather elegant!

New preprint: biorxiv.org/content/10.110… "Revealing non-trivial information structures in aneural biological tissues via functional connectivity" @DougBlackiston, Hannah Dromiack, @csgrasso10, @ThosVarley, Douglas Moore, Krishna Shrinivasan, @spornslab, @DoctorJosh, @Sara_Imari Connectivity networks of calcium signaling during injury response in Xenopus synthetic morphology

@michael_nielsen the dolomites!

What are your favorite Secular Cathedrals in the world?

@davisidarta @mihirraov @PNASNews i feel like the omics field in general needs more timepoints and higher quality datasets, instead of even more complex preprocessing pipelines

@davisidarta @PNASNews bold! especially re "if this was just an honest mistake. It isn't. The community was deceived by a few". What makes you say that? I thought a lot of the preprocessing methods that became de facto norm were developed to address practical limitations at the time, eg p>>n data

@wolfejosh 34, cult of luna repeats twice (not that you didn't know it before lol)

Music preference test. How many? 5: no signal 15: we are fast friends 20+: I understand you having never met you

@MaartenvSmeden most text tattoos suck, just like most research qs. so fairs

Every statistician will come to a point in their career where they feel like they have no choice but to get a tattoo with "what is your research question?" on their forearm

@connor_beem whats your email

If I ignored your first 6 emails, your 7th probably isn’t gonna push me over the edge.

@raulpacheco greg egan had one, but it recently broke after his roof collapsed l. he writes some stuff. sometimes

Have you written entire papers in your laptop? How about books? Does anybody still have a desktop computer?

@shauseth in my screen-free time im praising satan and doing some woodwork, clearly

idk why everyone is trying to decrease screen time. if you aren’t terminally locked in on a screen during the information age wtf are you doing

@jim_rutt these days politics in russia consists mostly of violence and other populist crap

Did Putin and Prigozhin cut a deal? Clown show!

@LinusEkenstam create art

If money was not an issue, what would you do in life?

@oncology_bg They should be called pharmas little helpers

Surrogate endpoints shouldn’t be called endpoints. They should be called putative surrogate measures to avoid confusion.

@MITMath Dr Strang, thank you so much for helping me understand (and enjoy?) all those pesky numbers. May many interesting papers come your way!

Prof. Gil Strang's last lecture is ... Monday! Watch it via live stream: grinfeld.org/strang/

@Simeon_Cps If the internet starts talking to us and writing songs with lyrics like in funkadelic's maggot brain

If we were one step away from an AI that starts recursively self-improving like hell (e.g. 1.1x in capabilities/day), how would you notice?