You can login if you already have an account or register by clicking the button below.
Registering is free and all you need is a username and password. We never ask you for your e-mail.
[+]Acerphoon0 points9 points9 points
ago
(edited ago)
[–]Acerphoon0 points
9 points
9 points
(+9|-0)
ago
(edited ago)
So the criticism is that the BJS sample size is too small.
Great, but it also seems to confirm other crime statistics, etc. So it seems to be true.
Also - At what point would the sample size become big enough? I fear this will be the same problem that we had with FST distance. where Lewontin or whatever his name was, found the FST distance between races to be at around 5-6% and said "it's too small to recognize subspecies".
When it was found that it was actually 12%, Lewontin obviously didn't change his stance. And frankly, no fst distance would ever be big enough to convince a race denier otherwise. So it's impossible.
And I think we have the same problem here. They will use the sample size as an argument, they will claim that it's too old, whatever. They will find any excuse they can, but at the end of the day, they won't change their stance anyway. I don't think any new, modern study with a big sample size would change their minds. It's really just an excuse.
I remember back in the elections I tried to suggest to someone 50 people sounded like a small number to extrapolate how a state would vote. Apparently that was a major thought crime.
Also - At what point would the sample size become big enough?
there's this confidence variable you jam into the equation, most people who talk about statistics on the internet don't know this.
See, I get this. I get the point they're trying to make.
But I don't think it actually matters to them. They're just using it as a convenient excuse in my opinion. The new BJS statistic doesn't even show race and ethnicity. - And I think that's for a good reason.
view the rest of the comments →
[–] Acerphoon 0 points 9 points 9 points (+9|-0) ago (edited ago)
So the criticism is that the BJS sample size is too small.
Great, but it also seems to confirm other crime statistics, etc. So it seems to be true.
Also - At what point would the sample size become big enough? I fear this will be the same problem that we had with FST distance. where Lewontin or whatever his name was, found the FST distance between races to be at around 5-6% and said "it's too small to recognize subspecies".
When it was found that it was actually 12%, Lewontin obviously didn't change his stance. And frankly, no fst distance would ever be big enough to convince a race denier otherwise. So it's impossible.
And I think we have the same problem here. They will use the sample size as an argument, they will claim that it's too old, whatever. They will find any excuse they can, but at the end of the day, they won't change their stance anyway. I don't think any new, modern study with a big sample size would change their minds. It's really just an excuse.
[–] squishysquid ago
I remember back in the elections I tried to suggest to someone 50 people sounded like a small number to extrapolate how a state would vote. Apparently that was a major thought crime.
there's this confidence variable you jam into the equation, most people who talk about statistics on the internet don't know this.
[–] Acerphoon 0 points 1 point 1 point (+1|-0) ago
See, I get this. I get the point they're trying to make.
But I don't think it actually matters to them. They're just using it as a convenient excuse in my opinion. The new BJS statistic doesn't even show race and ethnicity. - And I think that's for a good reason.