But that doesnβt justify using unweighted responses!
These are the unweighted proportions for years to graduation from the FIRE dataset: would Kaufmann infer that the true proportion of college students who are about to graduate surged by 74% and then collapsed by 30% since 2020?
16.10.2025 22:16
π 2
π 0
π¬ 1
π 0
The jump in the weighted proportion between 2023 and 2024 could very easily be downstream of a change in the weighting protocol. I donβt know the details here but I do know that since 2020 a number of surveys moved from 2 to 3 potential responses for gender ID
16.10.2025 22:16
π 1
π 0
π¬ 1
π 0
In response to this follow up from Kaufmann, I updated my post today to clarify that I donβt think the weighted or unweighted estimates are a good answer to this question
16.10.2025 22:14
π 1
π 0
π¬ 1
π 0
hey thanks (1) for saying so, I appreciate it (2) in a roundabout way, for your help--I haven't used my personal site for much but I remember referencing at least one post of yours when I first put it up
16.10.2025 13:59
π 1
π 0
π¬ 0
π 0
16 million views and a bunch of media write-ups for a claim that falls apart if you actually use the survey weights like you are taught to do in undergrad. I would say the University of Buckingham is not sending their best but realistically they probably are
15.10.2025 18:06
π 5
π 1
π¬ 0
π 0
There are a number of issues with this analysis but I found one that I haven't seen anyone else mention: Kaufmann estimates gender ID from the FIRE data without using the survey weights
When the weights are used as designed, the evidence for his core claim disappears
15.10.2025 05:11
π 23
π 6
π¬ 1
π 0
One on hand I agree with this and on the other Iβve been conditioned to feel like these accounts are an important part of the short form text post platform ecosystem
27.02.2025 14:23
π 2
π 0
π¬ 1
π 0
There are tons of these. Letterboxd, Craigslist, Goodreads
25.02.2025 22:00
π 0
π 0
π¬ 0
π 0
The world is much more complex than we can individually comprehend. If systems don't have ways of simplifying that ("attenuating variety" per Stafford Beer) then the variety will still be attenuated, just in a completely arbitrary way that leads to us prioritising completely the wrong information.
25.02.2025 14:54
π 10
π 2
π¬ 0
π 0
developing a sort of descriptive thesis that there is a growing anti-civilization movement coalescing around destroying the pillars of modernity: pharmaceuticals, efficient agriculture, and education and their assumptions are widely culturally accepted
17.02.2025 17:22
π 1058
π 173
π¬ 43
π 26
In a scenario where FDIC-backed assets are compromised Iβm not sure how useful your cash is going to be
09.02.2025 17:21
π 3
π 0
π¬ 0
π 0
05.02.2025 01:18
π 3
π 0
π¬ 1
π 0
Not. Permitted. Under the Law.
08.12.2024 14:21
π 205
π 18
π¬ 19
π 1
Pentametron was one of the great web art projects, retweeting couplets of accidentally iambic tweets. Thanks to Bluesky's open feed, I have resurrected the concept..
Behold @iambic.bot!
30.11.2024 15:26
π 1357
π 423
π¬ 36
π 66
Any way we could get the same range on the choropleth shades as the other one?
29.11.2024 06:13
π 1
π 0
π¬ 0
π 0
Also, this is just a weak form of the general observation that a billion is a surprisingly big number. You lose a lot of the unintuitiveness when you start counting at 200m. Two hundred million is a big number too!
27.11.2024 23:43
π 0
π 0
π¬ 0
π 0
I get irrationally annoyed by posts that begin like the quoted one. Donβt tell me what I canβt fathom, Iβm good at fathoming
27.11.2024 23:41
π 0
π 0
π¬ 1
π 0
You canβt fathom the difference between 0.002 and 1. This chart is to scale.
27.11.2024 23:39
π 3
π 0
π¬ 1
π 0
ποΈ
24.11.2024 14:58
π 0
π 0
π¬ 0
π 0
Manifesting works
21.11.2024 23:55
π 2
π 0
π¬ 0
π 0
tsdf?
21.11.2024 13:36
π 1
π 0
π¬ 1
π 0
a guy like that doesnβt worship god, he worships power
08.11.2023 19:24
π 333
π 5
π¬ 14
π 1
The current water level is 4189.5 ft above mean sea level
which compared with
1 year ago today is 0.91 ft higher β¬οΈ
2 years ago today is 0.38 ft lower β¬οΈ
10 years ago today is 4.51 ft lower β¬οΈ
as of Wednesday, October 25, 2023 at 06:15:00 PM MT
26.10.2023 01:13
π 1
π 1
π¬ 0
π 0
Do you do your own scans? For large format that actually doesnβt sound bad
20.10.2023 21:38
π 0
π 0
π¬ 1
π 0
Itβs so dark to see people grind all of this into content of the same flavor as everything else. βLaughing til my head comes off, whoβs in a bunker,β etc
12.10.2023 01:22
π 0
π 0
π¬ 0
π 0
The current water level is 4189.1 ft above mean sea level
which compared with
1 year ago today is 0.31 ft higher β¬οΈ
2 years ago today is 1.03 ft lower β¬οΈ
10 years ago today is 5.02 ft lower β¬οΈ
as of Monday, October 09, 2023 at 06:15:00 PM MT
10.10.2023 01:14
π 1
π 1
π¬ 0
π 0
tired of seeing videos of people dying on twitter, dragging my feet back over here
08.10.2023 04:01
π 0
π 0
π¬ 0
π 0
instead of a "severe thunderstorm warning," why not try a "gentle thunderstorm reminder"
14.08.2023 20:39
π 15
π 4
π¬ 0
π 0