Lightnews — Scholar-powered news

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 12h

#statstab #433 The Table 2 Fallacy: Presenting and Interpreting Confounder and Modifier Coefficients

Thoughts: Adding predictors to your model results in marked changes in inference. Be mindful!

#table2 #fallacy #covariates #bias #inference #regression

doi.org/10.1093/aje/...

The Table 2 Fallacy: Presenting and Interpreting Confounder and Modifier Coefficients

Abstract. It is common to present multiple adjusted effect estimates from a single model in a single table. For example, a table might show odds ratios for

doi.org

2 3

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 21h

🤣

1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 1d

Indeed. Diamond open access is more appropriate

1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 1d

#statstab #432 PsychOpen Gold

Thoughts: instead of submitting to greedy and unhelpful publishers, try this list of fully open and free journals in psychology.

#OpenScience #openaccess #apcs #goldaccess #pedagogy

psychopen.eu

PsychOpen GOLD: Open Access Publishing

We are a Diamond Open Access platform for psychology research. Peer-reviewed, free-to-read journals with no publication fees, promoting open science.

psychopen.eu

1 2 8

Reposted by Dr Mircea Zloteanu ☀️ 🌊🌴

Matti Vuorre @matti.vuorre.com · 12d

100% this, especially with Wiley given their anti-preprint stance.

Francesco Poli @francescopoli.bsky.social · 12d

Why are we still sending our work to Wiley and other publishing companies so that they can profit from it? There's so many better options now, for example: psychopen.eu/journals/

1 5 14

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 2d

My condolences.

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 2d

PowerPoint is still king for posters!

Reposted by Dr Mircea Zloteanu ☀️ 🌊🌴

Ruben C. Arslan @ruben.the100.ci · 2d

We're looking for an experimental psychologist in Witten. Contact me if you have questions about the job (I'm not on the commission, so can talk freely :-)
uni-wh.softgarden.io/job/59638545...

Universitätsprofessur für Experimentelle Psychologie (W2-analog) bei Universität Witten/Herdecke

Wir suchen: Universitätsprofessur für Experimentelle Psychologie (W2-analog) (Vollzeit) • Alfred-Herrhausen-Straße 50, 58455 Witten, Deutschland

uni-wh.softgarden.io

14 11

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 2d

#statstab #431 Attention Check Items and Instructions in Online Surveys with Incentivized and Non-Incentivized Samples: Boon or Bane for Data Quality?

Thoughts: We need more discussions on the "bad respondents" issue in research.

#Survey #quality

papers.ssrn.com/sol3/papers....

Attention Check Items and Instructions in Online Surveys with Incentivized and Non-Incentivized Samples: Boon or Bane for Data Quality?

In this paper, we examine rates of careless responding and reactions to detection methods (i.e., attention check items and instructions) in an experimental sett

papers.ssrn.com

1

Reposted by Dr Mircea Zloteanu ☀️ 🌊🌴

Richard D. Morey @richarddmorey.bsky.social · 4d

"Ultimately, contemporary AI is research misconduct"

I like it already :)

1 3 16

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 5d

#statstab #430 Modelling Count Data in Psychological Research: An Applied Tutorial

Thoughts: A fairly comprehensive frequentist tutorial. Covers some edge cases, but doesn't explain them well.

#count #poisson #negativebinomial #IRR #tutorial #education

doi.org/10.1002/ijop...

Modelling Count Data in Psychological Research: An Applied Tutorial

Across subfields of psychology, researchers frequently encounter count variables (i.e., non-negative integer values, which result from counted measurements). Although count variables are common in ps....

doi.org

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 6d

#statstab #429 A Vast Graveyard of Undead Theories: Publication Bias and Psychological Science’s Aversion to the Null

Thoughts: Ignoring null findings keeps bad theories alive.

#nulleffects #nhst #falsification #theory #critique #reproducibility #pvalue

journals.sagepub.com/doi/full/10....

A Vast Graveyard of Undead Theories - Christopher J. Ferguson, Moritz Heene, 2012

Publication bias remains a controversial issue in psychological science. The tendency of psychological science to avoid publishing null results produces a situa...

journals.sagepub.com

4

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 7d

#statstab #428 Knowing ANOVA

Thoughts: "Is ANOVA just a special case of regression? Maybe". We sometimes forget the benefits of specific cases of a linear model.

#ANOVA #FISHER #linearmodel #history #error #iid

www.linkedin.com/pulse/knowin...

Knowing ANOVA

Lost in space WARNING. I know nothing about agriculture and even less about spatial statistics.

www.linkedin.com

1 1

Reposted by Dr Mircea Zloteanu ☀️ 🌊🌴

Stephen Wild @stephenjwild.bsky.social · 7d

A meme with two panels. In panel 1 the woman looks disgusted. In panel 2 intrigued.

Text, panel 1: fake data.

Text, panel 2: silicon sample

8 22

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 7d

Is this the one where Calvin wanted to implement a form of SDT, that we emailed about with Matti?

1 1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 7d

I imagine it would screw up automated tools for extracting info also.

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 7d

agreed. it is often very annoying when you see that either someone names something very poorly, or that the "better" name is already used by like 3 other things (e.g., e-values vs E-values).

1 1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 7d

#stats Q: In frequentist, we use Confidence Intervals (CI). In bayesian, we use Credible Intervals (CrI or CI also). Given this overlap in initials, should we collectively move to Probability Intervals (PI)? Or does this confuse things with Prediction Intervals? Thoughts?

1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 8d

#statstab #427 Incorporating Historical Control Data Into an RCT

Thoughts: In frequentist stats, historical controls are a dangerous proposition. But in bayesian, they may have a more useful purpose.

#historicalcontrol #rct #bayesian #bias #priors #BMA

www.fharrell.com/post/hxcontr...

Incorporating Historical Control Data Into an RCT – Statistical Thinking

Historical data (HD) are being used increasingly in Bayesian analyses when it is difficult to randomize enough patients to study effectiveness of a treatment. Such analyses summarize observational stu...

www.fharrell.com

3

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 9d

#statstab #426 Execution of Replications

Thoughts: A good resource for conducting replications. Different ways to plan your sample size and consider "success/failure".

#replication #OpenScience #metaanalysis #samplesize #sesoi #smalltelescope

forrt.org/replication_...

6 Execution of Replications – Handbook for Reproduction and Replication Studies

How to carry out reproductions and replications in the social, cognitive, and behavioral sciences

forrt.org

1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 11d

It's the measurement error that gets in the way. You can have thousands of people do a specific task, but if that task isn't all that good then you have very precise rubbish.

1 1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 11d

And thanks for sharing the two links. I would like more papers that talk about benchmarks and their logic.

1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 11d

I saw someone argue on LinkedIn that our tools in psych lack the necessary precision to estimate small effects. So we should stick to around 0.40-0.80 SDs (bigger than that would be "an obvious finding")

2 1

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 12d

#statstab #425 Providing a Lower-Bound Estimate for Psychology’s “Crud Factor”

Thoughts: Psych research may not have the tools to investigate very small effects at all!

#crudfactor #research #psychology #mesurement #error #effectsize

gwern.net/doc/psycholo...

gwern.net

1 4

Dr Mircea Zloteanu ☀️ 🌊🌴 @mzloteanu.bsky.social · 12d

Can you say more about this?

(I'm thinking you mean the difference between saying "the data is not compatible with the hypothesis" vs "the hyp isn't compatible with the data" distinction?)