Mattan S. Ben-Shachar
LightNews LightNews
banner
mattansb.msbstats.info
Mattan S. Ben-Shachar
@mattansb.msbstats.info
3.3K followers 350 following 1.6K posts
Statistics lecturer | Freelance statistical consultant & research analyst | #rstats dev @easystats.github.io

home.msbstats.info

(He/Him)
Posts Replies Media Videos
Pinned
mattansb.msbstats.info
Mattan S. Ben-Shachar @mattansb.msbstats.info · Oct 26
1k followers! Calls for a re-introduction:

Statistics lecturer, freelance stats consultant, & #rstats dev @easystats.bsky.social 📊

I try to help social scientists make better inferences from their data & communicate their findings 👨‍🏫

Hope to bring the #stats twitter/R community vibes over to bsky!
mattansb.msbstats.info
#ISCOP2026 here we go!

Come find me to get an @easystats.github.io sticker 😉
February 10, 2026 at 1:37 PM
mattansb.msbstats.info
Funny and educational! Double whammy!
February 9, 2026 at 8:22 PM
Reposted by Mattan S. Ben-Shachar
chrisadamsecon.bsky.social
Chapter 23 openeclass.panteion.gr/modules/docu...
openeclass.panteion.gr
July 18, 2025 at 1:50 PM
mattansb.msbstats.info
Science reformists after the replication crisis: we should be more malicious with our science!

AI bros: or... or... hear me out... how about we offload as much as possible to SciBot™?

What are we gonna replication crisis 2.0?
February 9, 2026 at 8:27 AM
mattansb.msbstats.info
No surprises here
February 9, 2026 at 6:16 AM
mattansb.msbstats.info
"Is my sample large enough for Bayesian statistics?" is a weird question coming from someone who only ever uses frequentist stats that are only approximately correct for large samples.
February 8, 2026 at 3:26 PM
mattansb.msbstats.info
This show was too good.
Past/Present/Future
YouTube video by Brandon Roberts - Topic
www.youtube.com
February 8, 2026 at 1:04 PM
Reposted by Mattan S. Ben-Shachar
bharrap.bsky.social
Here's a silly Sunday read for you all

benharrap.com/post/2026-02...
The role of perceived sandwich origin on gustatory satisfaction: a study protocol – Ben Harrap
benharrap.com
February 8, 2026 at 9:15 AM
Reposted by Mattan S. Ben-Shachar
nposegay.bsky.social
but why is the save icon a vending machine
February 8, 2026 at 3:17 AM
Reposted by Mattan S. Ben-Shachar
andrew.heiss.phd
oooooooof
sonjadrimmer.bsky.social Sonja Drimmer @sonjadrimmer.bsky.social · 2d
Just put me on a flaming raft and push it out to sea.
Screenshot of a question posted to quora: "Why do older people not like putting spaces in file names when saving documents?"
February 8, 2026 at 3:41 AM
Reposted by Mattan S. Ben-Shachar
drcodyporter.bsky.social
Getting ready for the Perspectives on Scientific Error (PSE8) conference, taking place next week!

@mzloteanu.bsky.social @mattansb.msbstats.info

www.linkedin.com/posts/cody-n...
#scientificerror #methodology #statistics #investigativeinterviewing #liedetection #researchmethods | Dr Cody Porter
Our poster is almost ready for the Perspectives on Scientific Error (PSE8) conference, taking place next week! The poster focuses on why negative binomial regression models are important for research...
www.linkedin.com
February 6, 2026 at 3:36 PM
Reposted by Mattan S. Ben-Shachar
jbyoder.org
getting permabanned from research dot gov for turning in a 5-page Background section explaining that the effect estimates from a one-way ANOVA are in fact a model and therefore an algorithm and therefore Artificial Intelligence
February 6, 2026 at 12:06 AM
Reposted by Mattan S. Ben-Shachar
rbly.bsky.social
When you're wondering if the Pareto parameters are a hidden code asking after your mental health, it's time to seek help #statsky
February 5, 2026 at 7:33 AM
mattansb.msbstats.info
One of the most underrated plotting functions in #rstats is coplot(), which produces something similar to #ggplot2 's facet_grid, except that when conditioning on a numeric variable, it cuts it into *overlapping* ranges.
February 5, 2026 at 1:52 PM
Reposted by Mattan S. Ben-Shachar
xkcd.com
Groundhog Day Meaning

xkcd.com/3202/
Comic. [Person talking to person with black hat.] PERSON 1: Historically, it refers to a ceremony to predict the weather using a rodent. But nowadays people often use it to mean “a time loop experienced by one person.” PERSON 2: …What. [caption] Easily our weirdest holiday.
February 4, 2026 at 9:35 PM
mattansb.msbstats.info
Who was that guy? Obviously delusional...

Odds ratios *suck*, with their non-collapsability, what a mess...
mattansb.msbstats.info Mattan S. Ben-Shachar @mattansb.msbstats.info · Jan 9
Today, for a brief moment, odds ratios made sense to me. I understood the odds, their ratios. It was beautiful, like catching smoke in the palm of my hand. But that moment is now gone. Like tears in rain. #StatsSky
February 4, 2026 at 8:50 PM
Reposted by Mattan S. Ben-Shachar
devezer.bsky.social
I see many folks generate hypotheses exactly in this manner (w or w/o the AI) and design whole studies around something they came up with as they scroll the TL, and it's treated as standard scientific practice. We should be able to do better than this crackpot when it comes to hypothesis generation.
February 4, 2026 at 3:52 PM
Reposted by Mattan S. Ben-Shachar
davisvaughan.bsky.social
dplyr 1.2.0 is out now and we are SO excited!

- `filter_out()` for dropping rows

- `recode_values()`, `replace_values()`, and `replace_when()` that join `case_when()` as a complete family of recoding/replacing tools

These are huge quality of life wins for #rstats!

tidyverse.org/blog/2026/02...
dplyr 1.2.0
dplyr 1.2.0 fills in some important gaps in dplyr's API: we've added a new complement to `filter()` focused on dropping rows, and we've expanded the `case_when()` family with three new recoding and re...
tidyverse.org
February 4, 2026 at 11:39 AM
Reposted by Mattan S. Ben-Shachar
statsepi.bsky.social
Don't you f**king dare.
Screen shot of a youtube video titled "AI.FILL Function Explained: 10X Productivity in Excel with AI" with the caption "Let ChatGPT fill your missing data"
February 3, 2026 at 2:56 PM
Reposted by Mattan S. Ben-Shachar
gsimpson.bsky.social
🚨 GAMs have moved on—so it’s time for an update.

On March 3, 2026 (17:00–19:00 CET) I’ll be livestreaming an updated introduction to Generalized Additive Models in R

📺 YouTube livestream link: youtube.com/live/A9U8e1K...

#RStats #mgcv #GAMs #gratia #statistics 🧪
What's new in the world of Generalized Additive Models
YouTube video by Bottom of the Heap
youtube.com
February 3, 2026 at 12:57 PM
mattansb.msbstats.info
This is cool!
bchelsel.bsky.social Brian Helsel @bchelsel.bsky.social · 7d
R is a flexible programming language. You can even shape function syntax to resemble other languages. Here is an example of a ternary style operator with infix functions—the same logic as ifelse. Is this something you need? Probably not. But it is fun to explore these ideas within your code. #RStats
February 3, 2026 at 5:11 AM
Reposted by Mattan S. Ben-Shachar
requiemarm.bsky.social
they should make a movie series about how it’s irresponsible to use technology to mess with the natural order of things for profit
ign.com IGN @ign.com · 7d
Xfinity has just released its Jurassic Park-themed Super Bowl ad that features a digitally de-aged Sam Neil, Laura Dern, and Jeff Goldblum. https://bit.ly/4rmRhrK
February 3, 2026 at 3:32 AM
mattansb.msbstats.info
How does a study with N = 60 and no statistical inference (only point estimates) get published in 2026 in a psychology journal?

Is it because of the topic (LLMs)?

Can't imagine any "standard" psych paper getting away with not testing if a moderation effect is significant.

doi.org/10.1038/s415...
Assessing personality using zero-shot generative AI scoring of brief open-ended text - Nature Human Behaviour
Generative large language models (for example, ChatGPT and Claude) were used to score Big-Five traits from open-ended thoughts and video diaries. Large language model scores aligned with self-reports ...
doi.org
February 2, 2026 at 6:31 PM
mattansb.msbstats.info
#statsmeme
February 2, 2026 at 2:50 PM
mattansb.msbstats.info
Hot take? Johnson-Neyman plots are useful for basically all cases *except* for bi-linear interactions (for which they are almost exclusively used 🥲).

( #marginaleffects + #ggplot code in alt text)

#stats
library(tidyverse) library(marginaleffects) mod_lin <- lm(price ~ depth * carat, data = diamonds) plot_slopes(mod_lin, variables = "carat", condition = "depth") + aes( group = consecutive_id(p.value < .05), color = p.value < .05, fill = p.value < .05 ) + scale_color_manual( values = c("TRUE" = "blue", "FALSE" = "red"), limits = c(TRUE, FALSE), aesthetics = c("color", "fill") ) + geom_hline(yintercept = 0, linetype = "dashed") + coord_cartesian(y = c(-5000, 12500)) + labs(title = "lm(price ~ depth * carat)") library(tidyverse) library(marginaleffects) library(mgcv) mod_gam <- gam(price ~ te(depth, carat), data = diamonds) plot_slopes(mod_gam, variables = "carat", condition = "depth") + aes( group = consecutive_id(p.value < .05), color = p.value < .05, fill = p.value < .05 ) + scale_color_manual( values = c("TRUE" = "blue", "FALSE" = "red"), limits = c(TRUE, FALSE), aesthetics = c("color", "fill") ) + geom_hline(yintercept = 0, linetype = "dashed") + coord_cartesian(y = c(-5000, 12500)) + labs(title = "gam(price ~ te(depth, carat))")
February 1, 2026 at 6:52 PM