Crémieux Profile picture
Oct 4, 2024 • 10 tweets • 4 min read • Read on X
There are people who desperately want this to be untrue🧵

One example of this came up earlier this year, when a "Professor of Public Policy and Governance" accused other people of being ignorant about SAT scores because, he alleged, high schools predicted college grades better.Image
The thread in question was, ironically, full of irrelevant points that seemed intended to mislead, accompanied by very obvious statistical errors.

For example, one post in it received a Community Note for conditioning on a collider. Image
But let's ignore the obvious things. I want to focus on this one: the idea that high schools explain more of student achievement than SATs

The evidence for this? The increase in R^2 going from a model without to a model with high school fixed effects

This interpretation is bad. Image
The R^2 of the overall model did not increase because high schools are more important determinants of student achievement. This result cannot be interpreted to mean that your zip code is more important than your gumption and effort in school.

If we open the report, we see this:Image
Students from elite high schools and from disadvantaged ones receive similar results when it comes to SATs predicting achievement. If high schools really explained a lot, this wouldn't be the case.

What we're seeing is a case where R^2 was misinterpreted.
The reason the model R^2 blew up was because there's a fixed effect for every high school mentioned in this national-level dataset

That means that all the little differences between high schools are controlled—a lot of variation!—so the model is overfit, explaining the high R^2
This professor should've known better for many reasons.

For example, we know there's more variation between classrooms than between school districts when it comes to student achievement.

As another example, we know that achievement gaps exist along the whole continuum of school and district quality.

If the issue was really zip codes, high schools, and so on, this shouldn't be the case.

The other thing this professor should've known is that high school is biased! GPAs are biased too!

The bias in GPAs has actually been exploited: elite high schools inflate grades and don't report class ranks, so students appear better than they are. Image
But you know what isn't a biased tool for admissions? Just one thing: test scores.

Want to learn more? Here are some sources:

x.com/cremieuxrecuei…

cremieux.xyz/p/what-happens…

cremieux.xyz/p/bias-in-admi…

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Crémieux

Crémieux Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @cremieuxrecueil

Mar 10
On the left, you can see child autism diagnoses.

On the right, you can see states with policies that give schools more money when their students are diagnosed with autism.

When these policies pass, autism diagnoses increase by almost 25%! Image
Incentives really do matter for autism diagnoses.

For example, people on SSI receive larger payouts if they're diagnosed with autism.

After the economic downturn in 2008, the most heavily impacted age group started getting diagnosed with autism at an incredible rate: Image
Similarly, because laws in many places mandate providing more resources to autistic children, parents have sought to get their mentally retarded children diagnosed as autistic.

Using California as an example, more than a quarter of the rise 1992-2005 was due to this: Image
Read 12 tweets
Mar 10
The U.S. reports a higher maternal mortality rate than many peer nations like Canada, the United Kingdom, and France.

But the key word there is "reports".

How America classifies maternal mortality varies from peer nations, and this matters🧵 Image
If you go based on the official reports, America's maternal mortality has actually increased since about 1999.

Rising maternal mortality is a disgrace and a tragedy.

But that's if it's really rising. America's rise has more to do with this checkbox on death certificates. Image
The U.S. used to code maternal deaths as any deaths during childbirth or the immediate postpartum period, under the old ICD-9 classification.

When they switched to ICD-10, the classification expanded to any deaths during pregnancy, childbirth, or 42 days of the end of pregnancy.
Read 22 tweets
Mar 5
During Bernie's second set of questions in today's Senate confirmation hearing, @DrJBhattacharya came very close to describing the U.K.'s RECOVERY trial and arguing that the U.S. should emulate that sort of pragmatic clinical trial.

Bernie cut him off, but he shouldn't have🧵 Image
The RECOVERY Trial was the in-patient equivalent to the community-level PRINCIPLE Trial.

Both were trials run in the U.K. to figure out what works for keeping people off of serious treatments like ventilators and out of the morgue after they've been infected with COVID-19. Image
RECOVERY was an amazing success, but it can't be done in the U.S., because America's healthcare resources are not aligned like they are in the U.K.

In Britain, the NHS and the country's death index (how deaths are tracked) enable people to be easily signed up and tracked. Image
Read 11 tweets
Mar 5
There's a new GLP product that's even more effective than Semaglutide or even Tirzepatide: Retatrutide!

It leads to fast, and massive weight loss by not just suppressing appetite, but also by upregulating metabolism. Image
Side effects aren't the norm, and until you get to the high doses, they're uncommon and largely comparable to placebo. Image
This new GLP product also helps the liver a lot thanks to the addition of another ingredient beyond the GLP-1 and GIP in Tirzepatide: Glucagon, GCG. Image
Read 5 tweets
Feb 27
The Biden administration harassed police and fire departments for asking their recruits to have a bare minimum level of literacy, numeracy, and physical aptitude.

Today, the DOJ has dismissed all of those cases with a clear message:

Competence is legal again. Image
If you would like to understand the test questions that caused the Biden admin to go after these departments for 'disparate impact' reasons, I've written some threads.

Here are questions for U.S. v. Maryland State Police:
Here are questions for U.S. v . City of Durham and Cobb County:

Read 7 tweets
Feb 27
Today's big news is another DOGE development.

This one centers on modernizing how payments occur so that they're centralized, individually-justified, and accessible to the public.

If this works, there'll be clear, transparent accounting of everything the government pays for🧵 Image
This order starts off big.

The first thing it orders is creating a centralized system for logging payments issued by agencies.

Agencies already record this information, but this adds the need to consistently justify payments and to put all this together in an organized way. Image
Currently payment records are recorded in very disparate formats and inconsistently.

Some payments need to have justifications supplied already, and yet they're basically never justified.

People often just do not follow the rules!
Read 16 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(