utku turk @utkuturk.com · 21/09/2026just read this again, one of the greatest blogposts in existence statmodeling.stat.columbia.edu/2016/08/22/b...statmodeling.stat.columbia.edu Bayesian inference completely solves the multiple comparisons problem | Statistical Modeling, Causal Inference, and Social Science 110
utku turk @utkuturk.com · 19/09/2026Will try it soon, but I find writing in the Typst soooo much better in terms of experience. and now that they have HTML output, think about how better would be the journal experience with it! 000
utku turk @utkuturk.com · 12/09/2026A lot of people kept asking me "my participant did not see this item, I do not know why". that is usually just a csv error or some typo in their experiment. it is not a perfect tool, but it did a lot of work for me before. also after writing the initial shiny, I asked claude to make the ui fancy. 000
utku turk @utkuturk.com · 12/09/2026Here's a shiny app to check which item and condition will be seen by how many participants and how many times. www.utkuturk.com/pcibex-check/utkuturk.comShiny App 110
utku turk @utkuturk.com · 26/08/2026Will tackle a series puzzles surrounding productive machinery that creates complex lexical items that span across multiple syntactic positions. Will cover recent morphosyntax theories, which already substantially improve our account of how several syntactic positions are realized within one word. 020
utku turk @utkuturk.com · 26/08/2026Will be teaching my first class this year on morphology and production: LING 449U: How words are built. It is going to be based on my dissertation work. Here's the short syllabus: docs.google.com/document/d/1...docs.google.comLING 449U shortLING 449U: How words are built Tuesday and Thursdays 2:00 - 3:15pm, JMZ 1104 Instructor: Utku Turk Email: utkuturk@umd.edu Office Location and Hours: Marie Mount Hall 3416, By appointment Descripti... 170
utku turk @utkuturk.com · 14/08/2026gmorning to you, gmorning to me, and good morning to my 67 brms models 330
utku turk @utkuturk.com · 10/08/2026The preprint now includes a self paced reading experiment in Turkish, and through comparison of Czech "null" vs. Russian surprising case-ambiguity results in the light of no evidence for phonological modulation: osf.io/preprints/ps... 100
Reposted by utku turkPhilip Ball @philipcball.bsky.social · 10/08/2026"The central challenge is no longer building models that reproduce biological behavior, but building models from which causal structure can be inferred." Very sensible paper about not just throwing everything into your simulation or model. arxiv.org/abs/2608.06998arxiv.orgSimulating is not always understanding: When model complexity obscures biologyIn cell biology, computational models of biological systems range from minimal representations with a handful of parameters to whole-cell simulations tracking thousands of molecular species across a c... 911734
utku turk @utkuturk.com · 10/08/2026another blog post: www.utkuturk.com/posts/bayesi... this time on bimodality in person marking. i use turkish honorific addressee agreement on the verb (same as plural) and implement jammalamadaka & jin’s (2021) bayesian mode test in r (from scratch) 030
Reposted by utku turkClaus Wilke @clauswilke.com · 02/08/2026One of my pet peeves: People are obsessed with seeing/plotting error bars while also being confused about what they should represent. blog.genesmindsmachines.com/p/the-error-...blog.genesmindsmachines.comThe error bar cargo cultYou don't need to understand error bars. You just need to draw them. 78318
utku turk @utkuturk.com · 03/08/2026new blog post: www.utkuturk.com/posts/bayesi... ! i want both tables and the coefficient whisker plots, but i dont like how many things just cut through the text. so, i wrote an automated script that makes nice tables with whisker plots in tikz. 050
utku turk @utkuturk.com · 27/07/2026Thank you I happened to be very lucky and found it in its very early stages during my summer research in Turkey and was able to bypass many things and got to first ultrasound to the operation under a month! 110
utku turk @utkuturk.com · 27/07/2026While waiting for the operation, I was implementing a bayesian bimodality test in R following this paper: jammalam.faculty.pstat.ucsb.edu/html/Some%20... So hopefully will share it as a blogpost soonjammalam.faculty.pstat.ucsb.edu 010
utku turk @utkuturk.com · 27/07/2026Thank you! The only downside is that my voice is affected a bit, but I am not 100% it is a downside for everyone :D 000
utku turk @utkuturk.com · 27/07/2026Last month I got diagnosed with thyroid cancer, went through the operation 2 weeks ago, will go through some more procedures. But I am doing fine, I am healthy and I am recovering very well. 6190
utku turk @utkuturk.com · 05/06/2026Also here's my poster using Typst as well: typst.app/project/rIgB... Hopefully it is useful for someone!typst.appTypst 010
utku turk @utkuturk.com · 05/06/2026Here's my attempt at writing a Semantics Typesetting Guide for Typst: typst.app/project/rDI6... Hopefully soon I am going to write the Syntax version as well as the blog post. The best thing about Typst is that it immediately gives you a preview, compliation time is practically 0.typst.appTypst 121
Reposted by utku turkRadim Lacina @radlacina.bsky.social · 25/05/2026Turkish 🇹🇷 native speakers needed! I'm running a pilot sentence comprehension study in Turkish with an Erasmus student from Boğaziçi, it's only a short one (10 min tops I promise!). Please share and take part! Teşekkürler! farm.pcibex.net/p/eESOzY/farm.pcibex.netExperiment 145
utku turk @utkuturk.com · 15/05/2026if you want to show minute differences away from zero, just use point and error bars. if you care about "oh look big number and a small number", then just use pie charts. 010
utku turk @utkuturk.com · 15/05/2026just writing a code that takes any pdf and if there is any bar plots, it makes it a pie chart. because no one should be using bar plots. 110
utku turk @utkuturk.com · 15/05/2026i just think it makes it ***very*** hard to read. I think those discussion should exist either as a footnote, an appendix, or a separate paper 010
utku turk @utkuturk.com · 09/05/2026this was supposed to sound like a self-criticism, rather than outward directed criticism... 000
utku turk @utkuturk.com · 09/05/2026I have to say, none of the ordinal data plots I have seen online really make sense. 100
Reposted by utku turktj mahr 🤘 @tjmahr.com · 30/04/2026migrated a note about plotting probability allocations from ordinal regression models www.tjmahr.com/notes/2022-0...tjmahr.comVisualizing ordinal model probabilities with ribbonsHere is a ggplot2 recipe for plotting cumulative probabilities from ordinal regression models. 1185
Reposted by utku turkChengkun Li @chengkunli.bsky.social · 30/04/2026😀 Enter the amortized Bayesian workflow from here 👉 pipme.github.io/amortized-Ba... Huge thanks to my great collaborators: @avehtari.bsky.social, @paulbuerkner.com, @stefanradev.bsky.social, @lacerbi.bsky.social, @marvin-schmitt.com!pipme.github.ioAmortized Bayesian WorkflowAdaptive Bayesian workflow combining amortized inference with PSIS and MCMC diagnostics. 0219
Reposted by utku turkKirby Conrod @kirbyconrod.bsky.social · 30/04/2026new blog post about, like. why i teach syntax, i guess. may be a little bit inside baseball, curious about your thoughts kconrod.medium.com/build-me-a-b...kconrod.medium.combuild me a birdor, an apologia for (still) teaching syntax 6416
utku turk @utkuturk.com · 29/04/2026do you have to be a native English speakers? or is it okay for non native speakers to do the experiment as well? 110
utku turk @utkuturk.com · 28/04/2026people think that I am only harsh on their topic and talk. here's my take on experimentation, and the people's misleading trust in them. I feel like alchemy is a good allegory and a reminder for all of us to think. www.utkuturk.com/posts/alchemy/utkuturk.comjust don’t forget people pursued alchemy for 2500 years – utku turkexperiments are necessary and quite often not misleading, our blind trust in them is misleading. and I do not think the answer lies in being more careful with your stats, though that is also a must. 140
utku turk @utkuturk.com · 26/04/2026My sunday morning: I have been using β when reporting coefficients, but I have to say I really want to go back to θ. 000
utku turk @utkuturk.com · 23/04/2026And the reason I like this paper so much these days is this graph that I have been thinking about. Subjs who make agreement errors in Exp3 are faster to start speaking while in Exp4 they are slower. Funnily enough this is only the case with unaccusatives. 010
utku turk @utkuturk.com · 22/04/2026My favorite paper these days: www.sciencedirect.com/science/arti... "[I]t is hard to predict ex ante (i.e., before data collection) when errors will be fast or slow. [...] [We] validate a [...] model which successfully predicts when errors will be faster or slower than correct responses."sciencedirect.comErrors, fast and slowHuman errors in cognitive, attentional, and decision-making tasks are sometimes faster than correct responses, and sometimes slower, even for the same… 041
utku turk @utkuturk.com · 22/04/2026Reducing number of figures in a paper from 48 to 22 👍(i am crying inside) 010
Reposted by utku turkTom Gauld @tomgauld.bsky.social · 21/04/2026My latest cartoon for @newscientist.com 121215313
utku turk @utkuturk.com · 06/04/2026One thing that I like about Typst is that independent of how much writing or code you put in it, you do not have to wait more than a second for it to compile :D Once I get my stuff together, I am gonna try to recreate Mal's SynTex with Typst. 000
utku turk @utkuturk.com · 06/04/2026Is anyone using Typst? I realized it is a lot more easier to create documents and faster to compile with. Following what Mal did with SynTex, I want to create something with Typst, here's a lousy draft for semantics (github.com/utkuturk/typ...). Let me know what you would like to see more.github.comGitHub - utkuturk/typst-for-linguistsContribute to utkuturk/typst-for-linguists development by creating an account on GitHub. 130
utku turk @utkuturk.com · 31/03/2026most of the things on stats i learned was thanks to first with my MA advisor Pavel, and then advanced bayesian course in SMLP. I wish the world was a better place and travel was easier. but please apply, it is awesome! 020
Reposted by utku turkÖzge Bakay @ozgebakay.bsky.social · 30/03/2026I gave a talk at HSP 2026 @mit.edu, on agreement attraction in Turkish! We showed evidence for the role of structural positional associations in memory. This was joint work with @utkuturk.com, Duygu Demiray and @linguistbrian.bsky.social (that's me at the very back!) 181
utku turk @utkuturk.com · 25/03/2026Will be in Boston until the Sunday for HSP, would be happy to meet with folks that is around! 010
Reposted by utku turkVincent Arel-Bundock @vincentab.bsky.social · 03/03/2026Not sure what "entirely generated" means, exactly, but I feel we need new norms around this. Here's a blog I like about "etiquette", "consent", and what should be considered "rude" when sharing AI-generated content. Disclosures after the fact do not cut it, IMO. distantprovince.by/posts/its-ru...distantprovince.byIt's rude to show AI output to people | Alex MartsinovichFeeding slop is an act of war 54813
