# Thread: my solution to the public shooting problem in the U.S.

1. Originally Posted by Bamboo
This is where my stats skills aren't up to par. What does variance indicate?
Most mathematical notions are just attempts at making things precise so that we can apply measurements to things to test out hypotheses. Variance* is just a specific way of measuring the spread of a distribution of numbers.

The more spread out the individual numbers in a distribution are, the less likely a difference in averages, totals, or percentages between two categories is significant. Various ways to analyze variance are based on different assumptions. One thing I didn't have clear when I made my intuitive guess of significance was the high variation of whites in the general population since the 1980s. At this point I would not be expect significance based on race unless you allow some rather ridiculously high p-value.

Originally Posted by Marmotini
White men are 32 percent of the American population. White people who include women make up the statistics you quoted.

I feel like I am having a nightmare.
I personally was thinking about whites vs. non whites.

White men vs. non-(white men) is what you are analyzing. We have to be careful here because there are implicitly two coupled variables.

@Bamboo was analyzing (White vs. non-white) men. Thus, in a way he limited the "universe of discourse" to men. Considering that 99% of the shooters were men, this is in fact a reasonable approximation.

Bayes rule can be used here for inference:
The probability of being a white male given that the person is a shooter is 0.7.
The probability of being a male given that the person is a shooter is 0.99.
The probability of being a white male shooter given that he is a male shooter is then 0.7/0.99 which i still about 0.7.

The probability of being a white male given that the person lives in the U.S. is about 0.32.
The probability of being a male given that the person lives in the U.S. is about 0.50.
The probability of being a white male given that he is a male in the U.S. is about 0.32/0.50=0.64.

So the numbers work out to be pretty much the same whether we are considering race in the general population or race among men. We are assuming that race and gender don't correlate. But that seems like a reasonable assumption.

*Mathematically, the variance is just the square of the standard deviation. Alternatively, the varriance is the average(with small correction for sampling bias) of the squares of the distances of data points from the average of the set.

2. Originally Posted by ygolo
Most mathematical notions are just attempts at making things precise so that we can apply measurements to things to test out hypotheses. Variance* is just a specific way of measuring the spread of a distribution of numbers.

The more spread out the individual numbers in a distribution are, the less likely a difference in averages, totals, or percentages between two categories is significant. Various ways to analyze variance are based on different assumptions. One thing I didn't have clear when I made my intuitive guess of significance was the high variation of whites in the general population since the 1980s. At this point I would not be expect significance based on race unless you allow some rather ridiculously high p-value.

...

*Mathematically, the variance is just the square of the standard deviation. Alternatively, the varriance is the average(with small correction for sampling bias) of the squares of the distances of data points from the average of the set.
Hmm, ok. I'm sure an intermediate-ish online stats course would clarify this for me. Essentially you're saying...it doesn't seem like there's a strong correlation?

I personally was thinking about whites vs. non whites.

White men vs. non-(white men) is what you are analyzing. We have to be careful here because there are implicitly two coupled variables.

@Bamboo was analyzing (White vs. non-white) men. Thus, in a way he limited the "universe of discourse" to men. Considering that 99% of the shooters were men, this is in fact a reasonable approximation.

Bayes rule can be used here for inference:
The probability of being a white male given that the person is a shooter is 0.7.
The probability of being a male given that the person is a shooter is 0.99.
The probability of being a white male shooter given that he is a male shooter is then 0.7/0.99 which i still about 0.7.

The probability of being a white male given that the person lives in the U.S. is about 0.32.
The probability of being a male given that the person lives in the U.S. is about 0.50.
The probability of being a white male given that he is a male in the U.S. is about 0.32/0.50=0.64.

So the numbers work out to be pretty much the same whether we are considering race in the general population or race among men. We are assuming that race and gender don't correlate. But that seems like a reasonable assumption.
Basically, the last 4 or so posts have been aluding to this and I feel like I described it in my own way but the above says it cleanly, so I'm not going to beat this horse. Marm I hope you see I wasn't just 'limiting the universe of discourse' because of some sort of prejudice, but because that's just how the math works out.

3. Even by following ygolo's (correct) line of thinking, it may be argued that the probability of being a shooter while being a white male is the highest. Meaning that if I have three american males - one white, one black and one asian -, I have no further information on them and have to pick who is the likeliest to be a shooter, I can informedly pick the white male.
The base rate fallacy doesn't count in this case.

4. Interesting how so many people seem to be invested in missing the point... Even whilst confirming that this is an almost exclusively male problem, this fact doesn't appear to concern most enough to offer any kind of comment / solution, other than a shoulder shrug and a "what do you expect, men are more violent" dismissal. Really? That's all you have to say? You really think it's more important to bleat "UR RONG" at the OP than to tackle the issue under discussion?

What does that tell you?

5. Originally Posted by Salomé
Interesting how so many people seem to be invested in missing the point... Even whilst confirming that this is an almost exclusively male problem, this fact doesn't appear to concern most enough to offer any kind of comment / solution, other than a shoulder shrug and a "what do you expect, men are more violent" dismissal. Really? That's all you have to say? You really think it's more important to bleat "UR RONG" at the OP than to tackle the issue under discussion?

What does that tell you?
I dunno?.. I think it's fairly common on this forum for people to go off on a tangent in a thread to ensure that a particle of information is corrected or clarified.. Then someone who didn't bother to read any of that posts their reply to the OP, and it gets things back on track somehow.

No one did argue the fact that males are the more likely shooters by far. Only whether race should be a factor--and the consensus seems to stand that there isn't a race factor in the equation. I think it's an okay derail to clarify as the OP made a mention specifically on white males and not men in general.

I'm not quite sure what you're looking for here. Men and women alike are saying, "Yeah, we know thats how it is. Men cause more violent crimes by far." and no one is arguing that part of the issue. I know you're saying "Who cares if they're white or not! MEN are doing it!" But we already kind of know that. I don't know how that knowledge fixes the situation--but we weren't really looking for a solution to men being violent in the thread.

Just like Noll was saying--not all psychopaths even qualify for this. We're talking of a very small subset group (which most men cannot count themselves to be in at all) of psychopaths that shoot up and terrorize public places. Far beyond even 'normal' violent crimes like A&B and Aw/DW and AA and so forth. We're talking absolutely clear-cut terrorism.

Even though almost all of these have been male, addressing the issue as a male-oriented issue doesn't quite take enough to 'fix it' because the very vast majority of men do not ever function in this matter or regard. Predisposition to violence as a male is only a slice of the pie here. (And, as we're learning, being white isn't a significant slice as the OP seemed to stress on.)

I already mentioned my thoughts on the issue--we seem to have a policy of execution of terrorists. I happen to like that policy, even though I know most others find it barbaric and costly and etc.

6. Originally Posted by Salomé
Interesting how so many people seem to be invested in missing the point... Even whilst confirming that this is an almost exclusively male problem, this fact doesn't appear to concern most enough to offer any kind of comment / solution, other than a shoulder shrug and a "what do you expect, men are more violent" dismissal. Really? That's all you have to say? You really think it's more important to bleat "UR RONG" at the OP than to tackle the issue under discussion?

What does that tell you?
I get a little distracted by errors in statistical reasoning.

But the solution you posted earlier seems to me to be the most viable.

7. Originally Posted by kyuuei
I already mentioned my thoughts on the issue--we seem to have a policy of execution of terrorists. I happen to like that policy, even though I know most others find it barbaric and costly and etc.
I'm not opposed to the death penalty in cases like this either. Rarely is there any doubt of guilt, and the crimes are particularly heinous. I'm not sure why they get to live out the rest of their life while their victims weren't so lucky. I've never heard a good rebuttal to this for these kinds of instances.

8. Originally Posted by msg_v2
I'm not opposed to the death penalty in cases like this either. Rarely is there any doubt of guilt, and the crimes are particularly heinous. I'm not sure why they get to live out the rest of their life while their victims weren't so lucky. I've never heard a good rebuttal to this for these kinds of instances.
Not all do. OKC bomber was definitely sentenced to death.

9. Part of the premise presented by the OP was that white males commit this crime at a higher rate than other groups. If that's true, then it changes the way you approach the problem, because it suggests (more likely) a sociological issue in play (likely connected to other factors within that one group). If it's not true, than it suggests that the problem is quite possibly has to do with biological or more global factors, or some unidentified factor (like political action, social status, mental health, environment).

Why do I think this is this more than tangential? In fact directly connected to the central premises of what was presented?

Whatever the source of the problem is changes the way you try and fix it and classify it. I personally think there are different types of terrorism - whether they are connected to some sort of broad ideology with a political aim or they seem to be the act of one or two people who just want to wreak havoc. That, for me, changes the way you approach/punish/deal with them.

Based on what was found I'd reject the premise that mass shootings are a function of white entitlement. But any sort of entitlement? Can't say. I'd continue to assume that there is likely a mental health factor in play here, though that doesn't mean I'm especially hopeful for reforming them. How about a sociological explanation as to why men are so over-represented? I'm sure there is a factor here. So why not address it? Because sociological problems are by nature vague and often unclear, and there could be so many reasons it's hard to know where to start, and brainstorming is quite impossible when you can't get on the same page about hard details. I'm still listening for some ideas to consider.

10. Originally Posted by msg_v2
I'm not opposed to the death penalty in cases like this either. Rarely is there any doubt of guilt, and the crimes are particularly heinous. I'm not sure why they get to live out the rest of their life while their victims weren't so lucky. I've never heard a good rebuttal to this for these kinds of instances.
Executions create martyrs for their "causes", and give the culprits a quick, relatively painless end. Better to throw them into some standard maximum security prison, with the usual run of convicted felons, to languish in obsurity until they fall victim to standard prison violence.

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts
•