iiinova — where your digital self keeps evolving

Daniel Oberski @daob.nl · 19/10/2025

good example of a weak quasi-experimental design that is nonetheless convincing.

041

Daniel Oberski @daob.nl · 18/05/2025

Not in regular lists, which would be a closer equivalent to the given R code IMO.

040

Daniel Oberski @daob.nl · 18/05/2025

Interesting. How it thinks R should work *is* how Python works, and a lot of the coding benchmarks are very focused on python. Maybe that is the explanation?

110

Reposted by Daniel Oberski

Joran 🟥 @joranjongerling.bsky.social · 30/04/2025

🚨 PhD Job Alert/PhD Vacature🚨 English: Come work with Katrijn Van Deun, Katharina Loter, and me on "SEM2.0" in Tilburg! Nederlands: Kom met Katrijn Van Deun, Katharina Loter, and mij werken aan "SEM2.0" in Tilburg! www.academictransfer.com/nl/jobs/3514...

academictransfer.com

PhD candidate On the next generation of structural equation modelling tools

We are looking for looking for PhD candidate in Methodology and Statistics On the next generation of structural equation modelling tools

025

Daniel Oberski @daob.nl · 30/04/2025

Sending an email with this content to semnet (or wanting to) is all part of the circle of life Eiko. Generations of researchers have found out: semnet simply cannot change its nature, like in that scorpion story.

060

Daniel Oberski @daob.nl · 13/02/2025

I feel an instrumental variable hype coming on!

100

Reposted by Daniel Oberski

Tom Emery @drtomemery.bsky.social · 22/01/2025

This is one of the most exciting parts of our calendar. Apply to SICSS-ODISSEI!

076

Daniel Oberski @daob.nl · 20/01/2025

For those interested in latent class, latent profile, mixture modeling, model-based clustering, all of last year's materials, including R code, are available online: daob.github.io/latent-class...

daob.github.io

Latent class analysis

091

Daniel Oberski @daob.nl · 14/01/2025

Good to see you're still keeping up with socials during this time of reflection :p

110

Reposted by Daniel Oberski

Tom Emery @drtomemery.bsky.social · 29/12/2024

We have slightly updated our white paper on the future of Social Science Infrastructure in Europe. zenodo.org/records/1456... We would be very interested in hearing thoughts and opinions. The global data landscape is changing dramatically and we need to think critically about what we do next.

zenodo.org

European Social Science Infrastructure White Paper

Building on the achievements of recent years and envisioning a stronger alignment between the needs of the research community, we offer 7 clear recommendations for developments in Data, Computation, F...

052

Daniel Oberski @daob.nl · 02/11/2024

Anderson collected a lot more data than Fisher actually used for his example application in the LDA paper. What we did was feed some of that other data to many models at OpenML as well as the original LDA. I don't remember looking at overconfidence, but I'm sure you're right.

110

Daniel Oberski @daob.nl · 02/11/2024

I know you're joking but we actually did this. Linear discriminant analysis was still the best :D

110

Reposted by Daniel Oberski

ODISSEI @odissei.bsky.social · 26/09/2024

🚨 Call for Papers: European Social Survey Netherlands Community Conference 🚨 We invite colleagues from all disciplines using the European Social Survey to leverage our understanding of the social world. Submit your abstract by October 31💻 Learn more and apply👉 edu.nl/f9vmp #Sociology #cssky

edu.nl

European Social Survey (ESS) Netherlands Community Conference 2025 - ODISSEI – Open Data Infrastructure for Social Science and Economic Innovations

With the first release of the 11th wave of the European Social Survey, we would like to announce a Community Conference of the European Social Survey Netherlands. The conference will take place on the...

024

Daniel Oberski @daob.nl · 29/08/2024

There is no 1-1 conversion between probit and logit coefficients. Probit coefs are easy to interpret if you standardize the LRV ("STDY"): the coefficient is the number of sd's increase for a one unit increase of the predictor. Easy to convert to probabilities by pulling the prediction through pnorm.

030

Daniel Oberski @daob.nl · 11/07/2024

I.e. the sense is likely "more interpretable" rather than "obvious".

110

Daniel Oberski @daob.nl · 11/07/2024

I think they don't mean "intuitive" in the sense of "obvious" but in the sense that it gives some extra information: From V and the pattern of zeroes you can tell which linear dependencies are taken care of. E.g. if there's both age and year of birth in X, those will show up in one column of V.

110

Daniel Oberski @daob.nl · 10/07/2024

Thanks, this is *exactly* what I have been looking for!

010

Daniel Oberski @daob.nl · 02/07/2024

LISS has a basket option which automatically merges the time points/datasets you need. Is this what you mean? (also the "time-invariant" background variables tend to be simple copies, except when they are actually repeated; so a single copy is often enough, depending on the time period)

110

Daniel Oberski @daob.nl · 25/06/2024

I'm sure he would be delighted that he was able to bring down the number of his opponents to 1 in 5 in only 363 years! (sorry for the wonky colors btw)

130

Daniel Oberski @daob.nl · 25/06/2024

Quite. Hopefully it's all just measurement error from being confused by the question??

210

Daniel Oberski @daob.nl · 25/06/2024

Eurobarometer 38.1, 55.2, and 63.1. Provided without further comment.

Line graph showing the percentage of people believing "the Sun goes around the Earth" in 12 European countries, for the years 1992, 2001, and 2005. The averages for these years were about 10%, 30%, and 30%, respectively.

130

Daniel Oberski @daob.nl · 04/06/2024

i.e. I confused myself!

110

Daniel Oberski @daob.nl · 04/06/2024

I may have been confused by "gold standard": if you're doing observational data-causal inference but say you'd prefer to have an experiment, that implies you think that experiments are better. That crossed wires in my brain with your criticism of papers claiming experiments are not better.

110

Daniel Oberski @daob.nl · 04/06/2024

Ok thanks! I think I still don't fully understand the "temporarily embarrassed" bit, but those do sound like extremely vague arguments. (which issues, what complexity, what context, why is it important, how does something else account for context?)

110

Daniel Oberski @daob.nl · 04/06/2024

Even though LLM seem to me to be able to do this job reasonably well & more flexibly, there could be another reason to use regular expressions, when statcheck is used to check articles submitted to a journal: it encourages people to write the statistics in APA style.

000

Daniel Oberski @daob.nl · 04/06/2024

This is my experience too - seems to work fine as long as you give it precise instructions to use Python etc. There are some ways to force it into actually evaluating numbers even more.

100

Daniel Oberski @daob.nl · 04/06/2024

Hi Julia, this sounds like an interesting discussion, but I do not really understand what you mean. Which articles are you referring to? What kind of arguments do they give? And what do you mean by "temporarily embarrassed experimentalists"?

110

Daniel Oberski @daob.nl · 04/06/2024

@michelenuijten.bsky.social I assume you're already looking into this, but just to let you know, I tried out ChatGPT and it coped perfectly well with the example on your website. Might be a bit worse at certain things, bit better on detecting non-standard ways of reporting. Prompt below

100

Daniel Oberski @daob.nl · 17/04/2024

Very cool paper by Marta Kołczyńska and colleagues that cleverly brings together 1.7million survey responses in Europe over 30 years to show trends in political trust. ojs.ub.uni-konstanz.de/srm/article/...

ojs.ub.uni-konstanz.de

Modeling Public Opinion Over Time and Space: Trust in State Institutions in Europe, 1989-2019 | Survey Research Methods

030

Daniel Oberski @daob.nl · 26/03/2024

I'm not sure if it was supposed to be a statement about something, but the link to the "plain person's guide to social science" leads to a 404.

000

Daniel Oberski @daob.nl · 08/03/2024

OK but don't say they didn't warn you...

010

Daniel Oberski @daob.nl · 04/03/2024

They appear to be saying that, if the bias happens to be in the same direction as the effect, then it improves your decision rather than worsening it. The problem with that logic is that you don't know the direction of the effect: if you did, there was no need for data in the first place.

100

Daniel Oberski @daob.nl · 04/03/2024

What did you think of their point 2 Paul? ("avoiding confounding is less critical for decision making", Section 3.2 on pp 8-10). This point does not make any sense to me and I found the argument they give unconvincing.

140

Daniel Oberski @daob.nl · 26/02/2024

But what's the difference between saying it's "basically zero" versus "it's not exactly equal to zero"? Aren't you just rephrasing the thing you're criticising?

100

Daniel Oberski @daob.nl · 26/02/2024

stats dad joke of the year (so far)!

030

Daniel Oberski @daob.nl · 26/02/2024

Can you define "basically zero"...?

110

Reposted by Daniel Oberski

Matthew Salganik @msalganik.bsky.social · 25/02/2024

You can participate in a new scientific mass collaboration. The aim of the challenge is to measure current predictability of fertility outcomes in the Netherlands to advance understanding of fertility. Apply by March 24 at preferdatachallenge.nl

1913

Reposted by Daniel Oberski

ODISSEI @odissei.bsky.social · 26/02/2024

🥁Hurry! Only two days left to submit your application for the SICSS-ODISSEI 2024 Summer School. 📅Deadline: February 28th Access all details and apply using the following link👉 sicss.io/2024/odissei/ -- ccsky #StatsEd

004

Reposted by Daniel Oberski

ODISSEI @odissei.bsky.social · 20/02/2024

Apply for SICSS-ODISSEI Summer School 2024 before Feb, 28. 📍 Erasmus University Rotterdam, June, 17-28 💻 Python training and PreFer challenge: preferdatachallenge.nl 🌐 Access to CBS Microdata Participation is free including accommodation! Apply👉 edu.nl/g8kwr -- ccsky #StatsEd

edu.nl

Call for SICSS-ODISSEI Summer School 2024 applications is open

From 17 to 28 June 2024, ODISSEI is hosting its third summer school at Erasmus University in Rotterdam, as part of the Summer Institutes in Computational Social Science (SICSS) and the Erasmus Graduat...

148

Daniel Oberski @daob.nl · 18/02/2024

Tbf ik had het onderwerp van het artikel niet gelezen als "wanneer wordt AI slimmer dan de mens", maar als "waarom maken deze mensen zich zo'n zorgen".

030

Daniel Oberski @daob.nl · 06/02/2024

I think "psychomatrician" is fair: there are a lot of crazy matrices in psychometrics!

020

Daniel Oberski @daob.nl · 01/02/2024

Looks like they never got that far - they bet that they could get enough funding to become a drug development company and lost that bet: archive.is/yqxZa Two targets in trial phase so something *could* conceivably still happen, but...

archive.is

000

Daniel Oberski @daob.nl · 31/01/2024

(PS no irony: tell me more about this book I should be buying - I love buying books!)

110

Daniel Oberski @daob.nl · 31/01/2024

I feel so thankful for the amazing opportunity to read this AWESOME exchange #blessed 🙏

240