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

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

Apr 25
Why have autism rates risen over time?đź§µ

I have just put out an article dealing with numerous misconceptions about this topic, and a complete explanation of why autism diagnoses have become more common.

It starts with acknowledging that more kids are diagnosed than in the past: Image
But this is misleading for a few reasons.

One has to do with how this data was sourced. We didn't have a DSM with autism in it before 1980, so all the oldest people in this cohort were diagnosed as adults.

Adults are underdiagnosed. Go out of your way to diagnose? Same rates.Image
So something is off about this graph.

A major issue is that the older diagnoses here were done under a more arbitrary criteria: Autism has only been a described thing since Kanner's studies in 1943 and mass diagnosis kicked off in 1980.

Before 1980, diagnosis was often crazy:Image
Read 16 tweets
Apr 24
In 2016, researchers found that the minority-White wage gap was overestimated by about 10% because, at work, non-Whites tended to partake in more leisure, waiting around, etc.

They delayed releasing the study out of fear Trump would "use it as a propaganda piece." Image
They explicitly admitted that they let their personal politics get in the way of releasing a study with contentious but correct findings.

That doesn't inspire trust, but at the same time, given the topic, it might!
This isn't the worst example of scientists hurting the public for political reasons.

More infamously, this guy stopped the release of the COVID vaccines to prevent Trump from winning re-election in 2020, killing tens of thousands in the process. Image
Read 5 tweets
Apr 23
Aspartame?

What is it? Where is it from? What does it do? Is it harmful? What do health agencies think of it?

And why might the HHS be planning to ban it from American food?

Here's the aspartame review threadđź§µ Image
Aspartame is a sugary sweet synthetic molecule that's 200 times sweeter than sucrose.

More than half of the world's supply comes from Ajinomoto of Tokyo, better known for bringing the world MSG. Image
Because aspartame is so sweet, a little bit goes a long way.

The high levels of sweetness contained in very small quantities of aspartame make it ideal for making super low-calorie diet drinks like Diet Coke. Image
Read 34 tweets
Apr 22
When you match different American ethnoracial groups on socioeconomic status, the known differences in intelligence still persist. Image
This shows up in many datasets and persists whether using measures of parental or attained socioeconomic status:
This difference after SES stratification can be understood in dramatic terms.

For example, Asians with parents who merely graduated high school tend to be smarter than Blacks whose parents have graduate degrees.

Read 6 tweets
Apr 20
I don't think Bernie realizes what he's asking forđź§µ

The Bennett Hypothesis holds that universities alter their prices to capture additional funding that becomes available to students.

When Grad PLUS loans rolled out, the most exposed programs jacked up prices more: Image
If you want to "fix" this situation within reason, you need to cut funding.

Doing that has disproportionately negative impacts for the educations of people from socioeconomically worse off backgrounds. Or in other words, it hurts upward educational mobility for the poor.
Or, you could provide this presidential administration with a gift:

Centralize the universities and have the government more directly control all the funding. Make them "free".

This is far more likely than alternatives like 'Just give universities infinite money', but still bad
Read 4 tweets
Apr 16
Compared to twenty years ago, kids are eating some types of ultraprocessed foods more and some types lessđź§µ

For example, one thing there's proportionally less of is sugar-sweetened beverage consumption. Meanwhile, there's relatively greater sweet snack consumption. Image
Overall, the ultraprocessed food (UPF) consumption share is up across young ages to similar degrees.

The increase is definitely there, but it isn't dramatic. For example, going from 61% to 67.5% is an 11% increase in twenty years. Image
The increase in consumption is not differentiated by the sex of children.

In other words, boys and girls are both eating a bit more ultraprocessed food. Image
Read 14 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!

:(