Alon Zivony

BBS just issued the call for commentaries, and we would LOVE to get yours!! The deadline is October 15th, and the reference number is BBS-D-24-00489R2. Looking forward to hearing what you think about our suggestions for how to study unconscious processes!

I missed academic memes on my feed!

Staircase leading into a wall / into nothing.

Academic career symbolized in a picture.
#Ichbinhannah #postdocchatter

yeah, same. Up until now I just used repeated measures. But recently I've been venturing to individual differences and between group comparisons. I only now realise that things are much murkier than I knew.

Signal suppression makes search less effortful - Cognitive, Affective, & Behavioral Neuroscience Physically salient stimuli compete for attention but can be suppressed under certain conditions. Highly salient distractors can be suppressed more efficiently than less salient ones. However, the impl...

Hot off the press in a special issue at CABN! Here, Brian A. Anderson and I show that suppressing salient distractors is more effortful when the distractors are less salient: It's easier to suppress more salient distractors!

doi.org/10.3758/s134...

I just think that we're not trained on thinking what reliability does to our between-group effect sizes. Measurement error, yes. Reliability, no.

Exactly. Only that low reliability essentially massively increases within-group variability.

If a measure is unreliable and you happen to find very low within-group variability, the low variability might have happened accidently. So whoever tries to replicate will probably get a different outcome.

4. To make matters worse: large effects are often not very reliable. For example, the Stroop effect is easy to find, but the size of the effect changes wildly from one measurement to the next. So any between-group comparison of Stroop requires a large sample size to be replicable.

3. So the same rationale from correlations apply.

If our DV is highly unreliable, then effect sizes are small by default because low reliability=noise. The results of our between-group comparison are just not very replicable.

The only solution is huge sample sizes to allow for smaller effects.

2. Unless we're manipulating the groups, a between-groups test is essentially a correlation. Think about age groups. Instead of correalting a measure with age as a continious measure, we just nuch together people of different ages to a a single group.

Maybe this will help for intution:
1. If we have no reliability (test-retest r = 0), that means that any correlation we're finding is not replicable. After all, if a measure is not correlated with itself, how can it correlate with any other measure?
Weak reliability = less replicable correlation

I have a feeling that most psychologists have no intution why reliablity (both within-session and test-retest) is critical for between-group comparisons.

Which makes sense, I sure didn't think about it until earlier this year!

Can you share what you wrote?

This is what I found from a quick search (I can't find if the second was published):
pmc.ncbi.nlm.nih.gov/articles/PMC...
core.ac.uk/download/pdf...

okay, I saw some not well-cited papers. But my question is: why not correct for reliability? And why not do it often? We are essentially wasting away power by not tracking how (un)reliable our DVs are and adjusting our error terms for it.

When calculating a correlation we sometimes apply a correction for attenuation due to reliability.
Has anyone ever suggested a similar correction for a between-groups comparison?
After all, reliability of the DV affects those the same way (and they are often just a dichotomised correaltion).

Movie theory:
You know how there are androids in the Alien universe?
And you know how humans in the Alien universe always make really bad choices? (sticking their heads in alien eggs)

Hear me out:
Alien describes a future where people became increasly dumber due to a century of exposure to LLMs

Trans Legal Clinic need your support in funding this case. We all have a duty to do something, even sharing this will help, share it other platforms and to allies.

If you can please donate to help fund this case, this is the most important part of the restoration of the our rights:

I always love to help students understand what are the barebones assumptions of psychology as empirical science. That there's an objective reality, even for abstract concepts, and that our goal is to uncover it using methods and statistics. I find it helps with the "is psychology a science" debate.

Popular meme of guy holding up a sign that says "I just hope both teams lose"

Me: This project will distinguish between Theories A and B
My data:

I've published a pre-registration with @cvonbastian.bsky.social, @alonzivony.bsky.social, and Alicia Forsberg for my study on the unity and diversity of binding! Check it out! doi.org/10.17605/OSF...

(1/7) What is the best way to estimate subliminal thresholds in unconscious processing research? In our new preprint, we present STEP, a novel calibration method designed specifically for estimating subliminal thresholds osf.io/preprints/ps...

Ok, vision scientists. Are we doing the international beer exchange again this year at #VSS2025 as pregaming to Club Vision? Who’s in?

Still time to apply (until 30/04)!! What are you waiting for?

This might seem of no consequence whatsoever, but... if you're trying to use Excel to calibrate timestamps from two different machines to the millisecond, being half a second off can be a big deal!

Excel, who asked you to round up the seconds???

Probably my geekiest ever:
I just compared the now() function in Excel (which provide the time in hh:mm:ss) to Windows's clock. It turns out that, unlike Windows, the Excel second meter rounds up when milliseconds go over over 500! 🤯
So Now() is fully calibrated with Windows only half of the time!

Rob has closed quotes/replies now, but I wanted to expand on this: because I see it all the time from people who sincerely believe two things that are not supported by the evidence:

1) That biological sex is entirely immutable and entirely binary
2) That sex and gender are entirely distinct

1/?

Okay good, so it's all about scrubbing the website from any DEI related words, not actual content.

In my opinion, all of this is bad, but at least understandable.

My tiny last bit of hope is that they only scrubbed the website out of fear, not the program. If they cancelled the workshop... I don't know... I might not be coming back. But I'm clinging to hope.

Hey bluesky, does anyone know of any nice researchers studying trans issues in Amsterdam or not too far? I'm going to Amsterdam in June and I have some cool data about trans stereotypes and prejudice to share.

I have heard of so many LGBTQ+ grants terminated today. I am so sorry to everyone affected. This is devastating to our communities and to us as researchers. I have nothing more eloquent, comforting, or helpful to say. This is all just immeasurably horrible.