Milan Zarchev

"All else equal, a meta-analysis is the most reliable form of evidence" The average meta-analysis

We're thrilled to present you our latest special issue on the scientific reform movement! In response to the replication crisis and fraud cases in the behavioral and social sciences, a reform movement has arisen that pleads for a different culture and new practices... 1/2

@quantitudepod Never let me rho

CLASSIC QUANT LITERATURE! Change the title of a classic piece of literature to be about stat/quantitative methods. (Groan-worthy puns welcome.) (Please post by Thursday.)

If you think the art of satire bait died with the Onion, one academic is on a lifelong crusade to prove you wrong

@LNichollsStrath @UOSPsychology @strath_psh Congrats Professor Louise!!!

So happy to share that I have been promoted to Professor! Huge thanks to my colleagues, collaborators and students who have been so supportive over the years ☺️🙏🏼 I really love working where I first started studying psychology as an undergrad in 1997! @UOSPsychology @strath_psh

@VizeColin @EikoFried @schotz Unless you can find an older S, I'm afraid the s-factor breaks your naming convention sciencedirect.com/science/articl…

@EikoFried @MZarchev @schotz There's also an uppercase D-factor that predates the lowercase d(disease) factor. So not only do we have the whole alphabet, but also uppercase and lowercase letters. I say first to publish gets dibs on the uppercase letter for their factor psycnet.apa.org/record/2018-32…

New study finds that “neurodiversity characteristics” are best explained using a bifactor model with one general N factor”. I’ll just refer to my D factor blog, same problems. eiko-fried.com/does-the-d-dis…

@EikoFried @schotz I'll be the first to contribute if you start a collection of letter-factors!

@schotz Trend goes very much in the opposite direction. In fact I preregister they’ll have covered the entire alphabet by 2026.

@michelnivard @zenabtamimy Your github repo for this is an ideal to strive towards wow

@SolomonKurz No sorry the R package box (github.com/klmr/box)

@MZarchev You mean Box for cloud storage? I'm not so sure that's what I'm looking for.

What is the go-to #RStats package to handle dependencies across data files and scripts? My use case is how to juggle a print text and supporting online materials, both of which will depend on several data files.

@andrewheiss @rbjanis5 Hey this sounds like magic! Do you happen to have any resources that can take me from start to finish in making something similar?

@askryanair I was denied boarding bc of overbooking in July & missed a wedding. After 4 months, customer support told me they have no evidence that happened. I then filled out the EU form, posted to your headquarters. Still no response. When can I expect my compensation?

@Ryanair I was denied boarding bc of overbooking in July & missed a wedding. After months of waiting, customer support told me they have no evidence that happened. I then filled out the EU form, posted to your headquarters. Still no response. When can I expect my compensation?

Yesterday we had the honor to receive the Open and Responsible Science award of @erasmusuni and it was such a joy 🥳☺️ Thanks to our whole team who worked tirelessly (and for almost 3 years!) on #OpenScience♥️ Check them out👇 (cute 🐱 pic coming!)

@SolomonKurz Yes, an introductory course using... winBUGS. People shudder at hearing Bayesian afterwards

I am a _____ and my graduate department offers a course in Bayesian statistics.

@nbballou @rstatstweet To put words in the mouth of the infamous proponent of equivalence testing @lakens - a p-value can help you control your error rate for a one-tailed or two-tailed hypothesis. The one-tailed hypothesis test in particular is quite intuitive to implement with p-values

hoping this (potentially dumb) Q will get picked up by stats twitter: why use the two one-sided test (TOST) approach to equivalence tests, rather than simply interpreting the 90% CI relative to your equivalence bounds? is it just to get p-values to appease reviewers? #rstats

@rappa753 @levikul09 This looks neat! I'm now thinking it looks like a coefficient (some say tie-fighter) plot minus the confidence intervals and with an extra lollipop line. Wouldn't an audience that cares about correlation coeffs care more about uncertainty estimates? I like how it looks though!

I saw a cool idea from @levikul09 to visualize correlations with bars instead of colored matrices. Here are a few more ideas: 🍭 Use lollipops instead of bars 🎨 Avoid color gradient 📌 Pin labels to lollipops 🚨 Highlight selected pairs Details in 🧵 #rstats #dataviz

@joshthenormal Spring

👏🏾👏🏾👏🏾

Great gentle intro to BASH for #rstats nerds!

And we’re officially done!! 🎉🎉😍 2 intense days of teaching but lots of fun and learning! for PhD students by PhD students @SakSGhai @MZarchev @L_DallAglio @BingXu_estella @FassiLuisa @anabbmendes @elisabetbl