I've seen this thread pop up on my timeline a few times today. I just wanted to say that this claim is a racist dog whistle.
It all starts with this 4chan post where a supposed researcher claims that people with an IQ less than 90 can't understand questions like "How would you have felt yesterday evening if you hadn't eaten breakfast or lunch?"

source: knowyourmeme.com/memes/the-brea… Image
Later in the original thread, the author uses the same breakfast question found in the post on 4chan. Image
The breakfast question is frequently linked to memes implying black people have low IQs. Like this George Floyd meme. Image
Or this one, where they swap a black woman for the much more typical version of the meme which features a white man. ImageImage
See here, where this person suggests that this black teen isn't capable of understanding hypotheticals.

I don't know anything about this person but he's listed on the Southern Poverty Law Center website as a white nationalist. Source: splcenter.org/fighting-hate/… Image
On a personal note, I frequently get people on here asking me the breakfast question in a sad attempt to troll me as a black person on the internet. Image
I'm not accusing the original author of the thread of racism. Perhaps he is unaware of the origins.

But spreading these kinds of ideas without acknowledging the context is exactly how racist ideas get mainstreamed.

β€’ β€’ β€’

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

Keep Current with Kareem Carr | Data Scientist | πŸ“ŠπŸ“ˆπŸ“š

Kareem Carr | Data Scientist | πŸ“ŠπŸ“ˆπŸ“š 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 @kareem_carr

May 28
What is statistical bias? How does it relate to the usual meaning of bias? Read on to find out. Image
DEFINITION OF STATISTICAL BIAS Bias in statistics is the a...
People often use statistics to estimate unknown values in a mathematically and scientifically rigorous way.

Statistical bias is a way of measuring how good our estimation is.
Read 8 tweets
May 26
This is actually how "confidence intervals" work in statistics. I'm being 100% serious. Read on. This is a really fun concept.

Lots of people think of a confidence interval as being like the target in archery. Image
The confidence interval is fixed and the true value might end up in the interval or outside it. Image
Read 11 tweets
May 25
Statistician here. This is a joke from 1985. The joke is 100% of the kids can’t be above average. The joke is wrong. Image
Suppose you have 10 kids. All the kids have a pencil except 1.

That means the average number of pencils is 9/10=0.9.

Therefore, the 9/10=90% of the kids who have one pencil are above average.
If it was 100 kids who each had a pencil except for 1, a similar argument would apply.

The average number of pencils would be 99/100=0.99 pencils and 99/100=99% of the kids would be above average.
Read 6 tweets
May 25
Controversial opinion: More often that not, clusters (the things that come out of clustering algorithms) aren't real. They are products of an overactive mathematical imagination.
In my opinion, different clustering algorithms are just mathematizations of various subsets of these principles which don't have any deeper meaning than we were evolved to buy into them. Image
If you dig into the logic of what clustering is supposed to be doing, it’s actually kind of self-contradictory. Image
Read 4 tweets
May 23
WHY do we divide by n-1 when computing the sample variance?

Yesterday, I gave you one answer.

Today, here's a second extremely intuitive way of thinking about sample variance that you've probably never seen before. Image
You don't need to read Part 1 to understand Part 2. But if you missed Part 1, you can read all about it here:
Using a somewhat scary amount of algebra, you can show that the average distance between each individual observation and the sample average is equivalent to the average distance between every possible pair of observations. Image
Read 13 tweets
May 22
WHY do we divide by n-1 when computing the sample variance?

I've never seen this way of explaining this concept anywhere else.

Read on if you want a completely new way of looking at this. Image
BACKGROUND

This explanation is going to be confusing if you're rusty on summation notation. So here is a quick review.

If you're comfortable with this concept, skip to the next tweet.

Summation notation is a compact way of talking about adding up n values. Image
We should also quickly review the "sample mean" or "sample average".

If you are comfortable with this concept, skip ahead to the next tweet.

We compute the sample mean by adding up all our observations and then dividing by the total number of observations. Image
Read 15 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 on Twitter!

:(