iiinova — where your digital self keeps evolving

Reposted by Jay Jeffries, PhD

American Statistical Association History of Statistics @hos-asa.bsky.social · 21/07/2026

Few statisticians know that Frank Yates, pioneer of experimental design, is responsible for the annoying practice of indicating 3 tiers of statistical significance by stars (*p ≤ 0.05, **p ≤0.01, ***p ≤ 0.001). He soon regretted it and “vehemently opposed its unthinking use”. And here we are.

112954

Reposted by Jay Jeffries, PhD

Julia M. Rohrer @dingdingpeng.the100.ci · 20/07/2026

New paper out now 🥳 When psychologists discuss generalisability, they often refer to vague notions of representativeness. We provide an accessible intro to the total survey error framework as a tool to reason about this more rigorously. w @taymalsalti.bsky.social @ruben.the100.ci >

Thinking Clearly About Sampling and Representation With the Total Survey Error Framework

Collecting a sample that represents the population of interest well constitutes a challenge across the social and behavioural sciences. Psychology in particular frequently relies on convenience samples—most notably students and, increasingly, online participants—with a tendency to either (implicitly) assume representativeness without substantive justification, or to acknowledge a lack of it only in passing. In contrast, researchers rarely engage with the actual implications for their inferences, which undermines the generalisability of psychological findings. Critically, representativeness must be defined with respect to variables relevant to the target of inference, rather than superficial demographic diversity. Here we present the Total Survey Error (TSE) framework as a methodological tool that systematically addresses the multifaceted sources of error—particularly those related to representation—that emerge throughout the research cycle. Although TSE originated in survey research, its principles are broadly applicable to any psychological study seeking inference from sample to population. We offer practical strategies for identifying, preventing, and mitigating representation errors to improve the credibility and generalisability of psychological research.

Illustration of the total survey error framework with the representation strand highlighted. It shows how coverage error, sampling error and non-response error arise during the sampling process.

1027997

Reposted by Jay Jeffries, PhD

Mark Rubin @markrubin.bsky.social · 16/07/2026

Useful table of theory-related terms by @philippmusfeld.bsky.social et al. www.researchgate.net/publication/...

Terminology Table 1 summarizes the core terms used in the checklist. We define a theory as a set of interrelated propositions about (aspects of) the world that aim to explain and predict certain phenomena (Guest & Martin, 2021; Van Dongen et al., 2025). Theories typically do so by specifying mechanisms— accounts of how the entities, processes, and their organization described by the theory give rise to the relevant phenomena. We define phenomena as stable features of the world that may constitute the targets of theoretical explanation. In psychology, such features are often inferred from robust patterns of empirical observations, that is, observations that can be made repeatedly and by using different procedures (Bogen & Woodward, 1988). Notably, the assumption of the existence of the phenomenon may be false (e.g., due to errors in measurement). Theories typically consist of concepts (i.e., abstract ideas used to describe, differentiate, think about, or reason about certain aspects of the world), relations among these concepts, and further assumptions. Together, we call these the elements of a theory. Our terminology further adapts a semantic view of scientific theories. We assume that a theory is always expressed in some verbal form (i.e., in natural language) to communicate it to others, but it may also be expressed in, for example, a formal model. A formal model represents a specific version of (parts of) a theory expressed through formal means such as mathematical equations, algorithms, or logical propositions (Glöckner & Fiedler, 2025; Guest & Martin, 2021; Robinaugh et al., 2021; Smaldino, 2020; Van Rooij & Blokpoel, 2020). If a theory is expressed in a formal model, then, the elements of the theory are typically represented in the formal model by variables, parameters, constants, and the functions and operators that connect them. Together with any auxiliary assumptions added during formalization, these form the elements of a formal model. The same verbal theo…

2114

Jay Jeffries, PhD @jaybenjeff.bsky.social · 16/06/2026

I work in the field of education so topic could involve teacher-student relationships, parent-teacher relationships, peer bullying/victimization?

010

Jay Jeffries, PhD @jaybenjeff.bsky.social · 14/06/2026

I could see this becoming a team science group! (See manybabies.org/manymanys/) I’m interested 🤓

120

Jay Jeffries, PhD @jaybenjeff.bsky.social · 02/05/2026

Married my best friend @libbybrower.bsky.social this weekend at the @joslynartmuseum.bsky.social 🤍 The night itself felt like a part of the fine art around us!

000

Reposted by Jay Jeffries, PhD

Jacquelyn Gill @jacquelyngill.bsky.social · 29/04/2026

I am begging people looking to make major donations to universities to either 1) care as much about academics as they do sports, or 2) make unrestricted gifts instead. Signed, A faculty member at a university with brand new athletic facilities and crumbling teaching and research infrastructure

25985195

Reposted by Jay Jeffries, PhD

Brady West @bradytwest.bsky.social · 14/01/2026

A simple post: Why?

042

Reposted by Jay Jeffries, PhD

Elizabeth Jacobs, PhD @elizabethjacobs.bsky.social · 14/01/2026

Last night with no warning, RFK Jr. cancelled up to $2 billion in funding for mental health and substance abuse research and programs administered through SAMHSA. He and his minions did so because “they no longer believe the defunded programs align with the Trump administration's priorities”.

npr.org

Trump administration sends letter wiping out addiction, mental health grants

The Trump administration sent hundreds of letters Tuesday terminating federal grants supporting mental health and drug addiction services.

70753505

Reposted by Jay Jeffries, PhD

Jin X. Goh | 吴晋勋 @jinxungoh.bsky.social · 03/12/2025

ManuscriptCentral Wrapped! In 2025, you submitted 5 papers AND all got rejected 🎉 You spent 💯 minutes in total trying to submit your papers! You reviewed for 10 journals that would never publish your papers ❤️

2898

Reposted by Jay Jeffries, PhD

Andrew Gelman et al. @statmodeling.bsky.social · 01/12/2025

How much of “Mississippi’s education miracle” is an artifact of selection bias? statmodeling.stat.columbia.edu/2025/12/01/h...

statmodeling.stat.columbia.edu

How much of “Mississippi’s education miracle” is an artifact of selection bias? | Statistical Modeling, Causal Inference, and Social Science

0143

Reposted by Jay Jeffries, PhD

Demetri @phdemetri.bsky.social · 26/11/2025

I believe eigen fly. I believe eigen touch the sky.

324042

Reposted by Jay Jeffries, PhD

NSWERS @nswers.bsky.social · 07/10/2025

NSWERS has released a new research brief examining chronic absenteeism in Nebraska’s K–12 schools and its effect on student outcomes, including assessment scores, graduation rates, and college enrollment. View the full brief here: insights.nswers.org/briefs/2025-....

https://insights.nswers.org/briefs/2025-chronic-absenteeism

011

Jay Jeffries, PhD @jaybenjeff.bsky.social · 25/09/2025

This was state championship game in GI. The Islanders beat Creighton Prep to win the title.

010

Reposted by Jay Jeffries, PhD

Suiting Up Varsity @suitingupvarsity.bsky.social · 24/09/2025

Grand Island linebacker Jim Jefferies celebrates in 1978.

221

Reposted by Jay Jeffries, PhD

Kristen Panthagani, MD, PhD @kmpanthagani.bsky.social · 06/09/2025

A short explanation of p-hacking and why it absolutely makes sense to ask HHS to release the study methods of their autism report in advance.

781395567

Reposted by Jay Jeffries, PhD

Maarten van Smeden @maartenvsmeden.bsky.social · 18/11/2024

I made one for stats papers

15542148

Reposted by Jay Jeffries, PhD

Ian Hussey @ianhussey.mmmdata.io · 26/07/2025

If researchers find Cohen’s d = 8, no they didn’t. (probably.) Thoughts on the distribution of Cohen's d values in psychology and why we should think about their plausibility when reading articles.

mmmdata.io

If researchers find Cohen's d = 8, no they didn't

I’ve spent a lot of time thinking about the plausibility of standardized effect sizes in the last year. From a trustworthiness assessment perspective, (standardized) effect sizes have a great combinat...

26019

Reposted by Jay Jeffries, PhD

tj mahr 🤘 @tjmahr.com · 24/07/2025

note to self: 83.5% CIs will just touch 💏 at p = .05 www.tjmahr.com/unenv/#p-val...

tjmahr.com

Unevaluated expressions

261

Reposted by Jay Jeffries, PhD

Ben Marwick @benmarwick.bsky.social · 06/07/2025

Here is my checklist summarising a small set of some of the simplest tasks you can do that have high potential to improve the reproducibility of your analysis code. This is based on my year of reproducibility reviews for the J. of Archaeological Science: authors.elsevier.com/a/1lHjN_6yUM... 🧪🏺

Checklist of items researchers can do to improve the reproducibility of their code

310530

Reposted by Jay Jeffries, PhD

Joerg Lau @joerglau.bsky.social · 14/06/2025

Love this

8489118

Reposted by Jay Jeffries, PhD

Maarten van Smeden @maartenvsmeden.bsky.social · 23/12/2024

Let us start 2025 in a positive mood: here are 10 methods things researchers can worry *less* about in 2025

media.tenor.com

a countdown clock with the number 10 in the center

ALT: a countdown clock with the number 10 in the center

15259119

Reposted by Jay Jeffries, PhD

Jill Barshay @jillbarshay.bsky.social · 03/06/2025

Yesterday, June 2, was an interesting day at work. I was reporting a story about how the Education Department hadn't delivered a report to Congress on the Condition of Education, despite the June 1 deadline mandated by law. 🧵 (1/9)

518592

Reposted by Jay Jeffries, PhD

Lucien Hinderling @lhinderling.bsky.social · 02/06/2025

Inkscape plugin to rescale figures without distorting the text, and other useful features! github.com/burghoff/Sci...

615346

Reposted by Jay Jeffries, PhD

Anna Kornbluh @annakornbluh.bsky.social · 18/05/2025

say it again: 4 million people work in higher ed, the largest employer in 10 states, second largest employer in 10 more, and in 60 of the 100 biggest cities ROI for NIH and NSF for local economies is conservatively 4x, often close to 10x demolishing higher education is economic sabotage

6547951843

Reposted by Jay Jeffries, PhD

Kosta Derpanis @csprofkgd.bsky.social · 18/05/2025

A new use of the asterisk in the paper author list for credit assignment

841266

Reposted by Jay Jeffries, PhD

ProPublica @propublica.org · 10/05/2025

By slashing teams that gather critical data, the Trump administration has left the federal government with no way of understanding if policies are working — and created a black hole of information whose consequences could ripple out for decades: propub.li/3RZzqHP 📽️: @josesepulveda.bsky.social

35952321

Reposted by Jay Jeffries, PhD

moin syed @syeducation.bsky.social · 05/05/2025

Recently did the annual walk through of our totally normal publishing system for my undergraduate research methods students. Never fails to boggle their minds.

a slide showing the ridiculous process of publishing a journal article, highlighting how universities both pay for the work to be done and then pay to access the work.

515254

Reposted by Jay Jeffries, PhD

Kelsey Hightower @kelseyhightower.com · 19/04/2025

Train your own model.

A medical illustration of the human brain.

211288185

Reposted by Jay Jeffries, PhD

Julia M. Rohrer @dingdingpeng.the100.ci · 25/03/2025

I asked DeepSeek to develop a scale to measure addiction to addiction scale development and of course it delivered.

1816747

Reposted by Jay Jeffries, PhD

Senator Bernie Sanders @sanders.senate.gov · 11/03/2025

Let’s be clear: the Dept. of Ed. provides resources to 26 million children living in high-poverty school districts; Pell Grants to over 7 million students; & funding for millions of children with disabilities. Closing its doors would be a disaster for working class families.

17342841081

Reposted by Jay Jeffries, PhD

KiDLAB @kidlab.bsky.social · 02/03/2025

🟣 This is the eighth interview in the BOLD series on our special collection. Catrin Finkenauer explains why schools and educators need to earn students’ trust—especially in those from financially insecure backgrounds—to prevent school dropout. boldscience.org/why-schools-...

boldscience.org

Why schools need to earn students’ trust

Students who distrust institutions are more likely to drop out of school

043

Reposted by Jay Jeffries, PhD

Mark Rubin @markrubin.bsky.social · 26/02/2025

A Guide to Multiverse Analyses "The large array of defensible options available for researchers to select along the workflow creates what is known as the ‘garden of forking paths’." Preprint: doi.org/10.31222/osf...

15519

Reposted by Jay Jeffries, PhD

Jess Calarco @jessicacalarco.com · 22/02/2025

I always shock my students a bit when I tell them that quantitative data is just qualitative data that has already been interpreted numerically.

19719163

Reposted by Jay Jeffries, PhD

Rafe Meager (they/them) @economeager.bsky.social · 14/02/2025

let's see what DOGE has been cancelling at the department of education. @stuartbuck.bsky.social went through the list. will link to his post at the end of the thread. i will start with his 4th example: foundational research to understand how american kids are doing at school

3222106

Reposted by Jay Jeffries, PhD

Tanya Shapiro @tanyashapiro.bsky.social · 12/02/2025

more and more i'm gravitating towards the title of "data generalist." i do a little bit of everything. some things better than others. and the rest we'll figure out as we go.

1321

Reposted by Jay Jeffries, PhD

We Are RLadies+ @weare.rladies.org · 03/02/2025

♓ Pisces (Feb 19 - Mar 20) → {quarto} Dreamy, adaptable, sentimental. Loves a good narrative, but sometimes gets lost in the details. Might spend hours formatting a document instead of finishing the analysis. 📖✨ (4/13)

151

Jay Jeffries, PhD @jaybenjeff.bsky.social · 04/02/2025

Thanks for this explanation! Can you think of an example where the \(x) approach would be more appropriate over the ~function() approach? I often rely on the latter but would love to know when I need to resort to \(x) 😅

100