Bite Size Psych
The early 1940s,
Berkeley’s University was sued for sexual discrimination
based on this statistic.
44% of male applicants got accepted
whereas only 35% of female applicants got accepted.
Furthermore, there is less than a 1 in 10,000 chance
that this 10% gender gap is due to chance.
The question is: can you say this is evidence of sexism?
It all seems quite convincing.
But what if I told you that in the above case,
it was actually the males who are getting discriminated against.
To show you, let’s break it down into the separate departments.
The thing to note is that in most departments,
it was actually women who are more likely to be admitted.
And yet strangely when you take the average,
the opposite seems true.
What’s going on?
Well, the answer is actually hidden in plain sight.
Pause this video to see if you can figure it out.
Okay. So the problem is:
We saw a 10% gap
and immediately assumed it was due to gender discrimination.
But the real reason was that women tend to apply for courses
which are harder to get into.
Whereas males apply for courses which are easier.
As such women were getting rejected more often.
For example, take a look at department A compared to E.
A has a much higher acceptance rate than E.
Yet compared to men,
women are shying away from A and flocking to E.
This phenomenon in which trends against different groups
disappear or even reverse when averaged.
It’s called the Simpsons paradox.
Here’s another example.
Look at the start-up on death penalty’s in Florida.
4.8% of white suspects for the death sentence
compared to 2.5% of black suspects.
Now you can imagine people who believe racism doesn’t exist
using this statistic in a debate.
They could argue that if there’s any bias,
it’s against the white suspects, right?
But let’s break it down based on the victims and suspects race.
So in the top left corner
when a white suspect kills a white person,
4.9% of them got sentenced to death.
However, in the bottom left corner,
when a black suspect kills a white person,
12.6% of them got sentenced to death.
Another important thing to notice is
that when a white person was killed,
the sentences were harsher compared to when a black person was killed.
This all suggests that there is racial bias within the justice system.
Yet once again the overall averages save the complete opposite.
So what’s going on here?
Well, white people tend to kill other white people,
whereas black people tend to kill other black people.
Therefore sense cases with white victims got harsher sentences on average,
white suspects got a higher percentage of death sentences.
Now the Simpsons paradox is merely one way statistics can mislead you.
There are countless more.
And at this point, a lot of people get disheartened
and take this to mean we shouldn’t trust statistics at all.
But all this really means is that the general public
needs to get a better grasp of statistics
before they are bombarded with stats
from news outlets, politicians and infographics.
The Simpsons paradox is simply a demonstration of
just how easily numbers can deceive us.
伙伴们 顺便说一句 我最近创建了一个patreon账号
By the way guys, I’ve recently set up a patreon account,
so if you like my stuff and want to see more then go and check it out.