Stephen Wild

To my health researcher colleagues: when you're looking at routinely collected data (over many years) and you're interested in the relationship b/w two kinds of events (say, diagnosis for diseases A and B), how do you best deal with time gaps (eg people moving)? Obviously these introduce time bias >

ht @thoughtfulnz.bsky.social

@tslumley.bsky.social does a much better job than I do.

Fair.

I had the divide as being between "tangible" and "intangible" outputs, but "people" and "objects" is also a good way to think about it.

My bigger complaint was that many of his bullshit jobs were in fact useful, just not in a way where it was easy to map work -> output

The podcast episode may temporarily turn me into a Graeber stan

I concur.

The within-country comparisons are fine, but some of the other comparisons are uninterpetable given this weighting acheme

bsky.app/profile/step...

No, this is exactly it. Plus not properly accounting for the sampling scheme when presenting some of the results

bsky.app/profile/jona...

It does, yes. But I am not sure if they adjusted for sample size differences across countries

Indonesia and Malaysia have large Muslim populations. You will sometimes hear that in Islam a wife has "a duty to obey her husband." Obey in this sense has a different meaning than I think the survey fielders are after

And sample sizes are different for the different countries. See also:

bsky.app/profile/step...

Ask yourself a question: why might the results for Indonesia, Malaysia, and India be so different from the other countries?

They use different sample sizes for different countries, and it's not clear to me from a quick scan how they adjusted the aggregate statistics for it.

Survey report here:

www.kcl.ac.uk/assets/news/...

The data is weighted so that the composition of each country’s sample best reflects the demographic profile of the adult population according to the most recent census data. “The Global Country Average” reflects the average result for all the countries and markets in which the survey was conducted. It has not been adjusted to the population size of each country or market and is not intended to suggest a total result.

Hell of a note:

Gen Z males twice as likely as baby boomers to believe wives should obey husbands Global survey shows young men and boys hold more traditional views about gender roles than older generations

The Guardian article in question:

www.theguardian.com/world/2026/m...

The country by country breakdown. Most respondents agree in Indonesia, fewest in Sweden.

Show the country breakdown next time you cowards (as I shake my fist at The Guardian)

Oof. Bad question.

Try this one!

bsky.app/profile/step...

Learning From the Mess What the vitamin story tells us about reproducibility, discovery, and human nature.

What the vitamin story tells us about reproducibility, discovery, and human nature.

The literature can often support multiple or contradictory ideas. Just because I don't like Graeber's style of engagement with the literature doesn't necessitate his ideas being wrong.

Coming back to this, "tendentious" is probably the wrong word. Maybe "polemical reading" is a better description

bsky.app/profile/step...

bsky.app/profile/step...

Scream it from the rooftops

Fair point.