Pavel Logacev

For the last couple of months I've been working on something and I'm excited to finally share an early preview:

Say hello to plumber2 🎉

plumber2 is a full rewrite of the plumber package for creating powerful webapis in #rstats. It takes everything we have learned from plumber and adds even more

Social-Media-Posting von Julia Ruhs @juliaruhs Das gefällt vielleicht nicht jedem, aber NDR und BR starten ein neues Format - für mehr Meinungsvielfalt. Wir haben in de letzten Jahren zu oft unliebsame Themen + Meinungen ausgeblendet. Thema der 1. Folge: Migration. Morgen in NDR, bald auch auf YouTube + im BR. #klar

Seit Jahren wird kein Thema medial so unerbittlich hochgepeitscht wie Migration. Als Fernsehsender kann man natürlich weiterhin auf diese Karte setzen. Aber zu behaupten, das sei ein "unliebsames Thema", das "ausgeblendet" worden sei, ist dann halt gelogen und demagogische Propaganda.

Today, in Istanbul’s Maltepe district, over 2.2 million citizens, according to organizers—took to the streets, demanding democracy, justice, and freedom in the face of Erdoğan’s increasingly authoritarian rule.

Also newsworthy is that this many people took to the streets despite a week of intense police violence, lawless detentions and arrests.

AI obsession is completely out of hand. We have seriously arrived at a point, where some people prefer feeding 1TB of data to an LLM to de-duplicate instead of calling DISTINCT on a database. 😱

Our introduction to Bayesian Data Analysis underwent a major revision (it was too long at 1000 pages, so we moved some 400 pages into online). Currently in production but freely available forever:

bruno.nicenboim.me/bayescogsci/

I just posted a new notebook:

Causal Inference with the 𝚖𝚊𝚛𝚐𝚒𝚗𝚊𝚕𝚎𝚏𝚏𝚎𝚌𝚝𝚜 📦 for #Rstats. It introduces the idea of G-Computation and tries to demystify the differences between ATE, ATT, and ATU.

This is a first draft and I would looove any feedback!

marginaleffects.com/chapters/gco...

I suggest random changes to people's prices for stuff.

Wahlwerbung für die AfD: »Welt«-Meinungschefin kündigt wegen Gastbeitrags von Elon Musk Die »Welt am Sonntag« veröffentlicht einen Gastbeitrag, in dem Techmilliardär Elon Musk für die AfD wirbt. Mitarbeitende der Redaktion sind empört. Meinungschefin Eva Marie Kogel reicht ihre Kündigung...

-
Eine "Welt"-Redaktionskonferenz stelle ich mir etwa so vor: ein Haufen eingebildeter Edelfedern, die für jeden Dreck zu haben sind, wenn sie damit nur den Gang zum Arbeitsamt vermeiden können. Ausnahmen bestätigen die Regel.
www.spiegel.de/kultur/elon-...

Thank you! Yes, absolutely. I'd be happy about any help. :)

Sell Smart: Inventory Guru - Inventory Guru: Smart Inventory Replenishment | Shopify App Store Helps merchants forecast product demand, prevent stockouts, and optimize inventory levels with automated alerts and financial impact analysis for re-orders.

I just finished my fist Shopify app (apps.shopify.com/inventory-guru). Happy to connect with other other Shopify folks.

Our Introduction to Bayesian Data Analysis for Cognitive Science (with Nicenboim and Schad) is now in production with CRC Press. It will remain freely available here:

bruno.nicenboim.me/bayescogsci/

Funny story. Submitted a stage 1 registered report in 2021 to an open access journal, the stage 2 has now been accepted as of two weeks ago, but the grant we would’ve used to pay the APC is long closed and I’m no longer affiliated with a university. lol.

years ago a friend ask whether I care about writing papers. I remember answering with sth like "oh I just hope people somewhere in the world will read them one day." today I woke up to some messages that one of my papers were included as a part of a syllabus somewhere, and made me really happy :)

German word for the special type of guilt you feel when you throw away your kid’s crafting projects because while they all embody cherished memories, there’s just no way you’re going to keep that piece of paper with two chestnuts and a bottle top glitter glued to it.

Regular reminder that "an outlier" doesn't exist. Outliers only exist in reference to some assumed distribution, they are essentially data that didn't come from your assumed distribution.

😱

My paper (with Pavel Logacev) is out! doi.org/10.1080/2327... We tested case syncretism and its effects in Turkish agreement attraction. Unlike what is predicted by cue-based retrieval models, we (N=118) found no effect of case syncretism on the magnitude of the attraction.

The next paper should deliver a theoretical proposal that is compatible with both.

Keines deiner Probleme ist darauf zurückzuführen, dass jemand Sozialhilfe bezieht oder nicht aus Deutschland stammt.

isso

Unfortunately, small-sample-size studies are so common in psychology that some believe much of psychological research is statistically unfalsifiable (Morey & Lakens, 2016). We suggest that a prediction interval that is extraordinarily wide only because of the sample size of the original study is an indication that the findings of the first study may be unfalsifiable. Indeed, a wide interval could indicate that validating an initial study is not worthwhile given the error associated with it. In this situation, it might be most appropriate to discard the conclusions from the original study and conduct a new, well-designed study instead. That is, the new study is not viewed as replication but, rather, as the first meaningful source of information on the original question.

#StatsSky #rStats

Here's a fantastic tutorial by Jeffrey Spence on prediction intervals with practical examples using the predictionInterval package in R: journals.sagepub.com/doi/10.1177/...

Will definately be adding PIs to esci.

I especially like this bit:

A scatter plot with two model fits. One increases then gently decreases (red). The second increases and then remains flat (blue).

Just an interesting crossvalidated question about monotonically increasing GAMs with other constraints. Didn't know mono-increasing GAMs were so easy to fit.
stackoverflow.com/questions/66... #stats