Summations Only

Tangle speculates humorously: *wink*

Well there's a thing....just lucky I guess.

Why not try a polynomial or exponential curve to see if you get a better fit to the data?Enjoy

Wouldn't a high homicide rate negatively impact one's rating in the Human Development Index? (Answer - yes it would, by depressing life expectancy, which is a term in the HDI.)

And your policies would send them to those places as well, only with bombs instead of guns. Guns aren't causing people to become angry and insane. The cause needs to be addressed. But the cause isn't the availability of firearms. The cause isn't a "mental break" when we're looking at incidents that reflect months or even years of planning.I don't know how you get people to stop doing bad things, forever. It's clearly not a problem the UK has solved. I don't think it's solvable.

It can't be that significant an effect --- America made the list.If you want no interaction at all, it's difficult to see what criterion for affluence we could use. GDP per capita? But skilled workers get killed in countries with high homicide rates. Damn.

And I keep repeating that it's not what I'm missing about statistics - I have a minor in mathematics, after all - it's about what you're missing about statistics. Like the limitations of statistical inference. Like the way that sample selection can be used to mislead. Those are all things you don't seem to know anything about, so when I see you produce statistics and draw improper influence via the Ecological Fallacy, when I see you flaunt a clearly cherry-picked statistical sample, it seems unlikely that I'm wrong and you're right. If you're right, it would be by accident. And why should I accept that you're accidentally right?If you expect your arguments to be convincing then not making elementary statistical errors would be step one. I don't expect anything, I simply expect your description of the graph to match the graph. You said that "the line must rise from 0,0." But it doesn't. It doesn't even go through 0,0. It rises from an origin you defined in the software as "-1, -1." I know you did that because what you posted is a screencap of your software. But we don't know that. There's no reason to assume that. At the margin, assuming 0 guns in the United States, some person in the United States could eventually be shot by a Canadian from their side of the border, and that'll be one gun death associated with zero guns (since the gun never was in the United States.)And you're still describing a line that rises from -1, -1 as rising from 0,0. But it doesn't. The mechanism is obvious - people using firearms to prevent themselves or others from being murdered. Since only the rare self-defense situation requires the gun to even be fired, it's not unreasonable to expect the overall rate of gun deaths to be reduced. Is it true? I couldn't say. None of the data supplied so far has been relevant to that. There's no statistical measure of "people that would have been murdered but weren't."

Why do we need a criterion for affluence at all? I don't understand why you think there's justification for bracketing our sample around a specific range of "affluence" except to exclude by definition those countries with incredibly high homicide rates and low gun ownership.

Great, but all of Percy's arguments about feelings versus statistics apply, here. The cameras haven't had any reductive effect on crime in the UK. They're not even useful for catching criminals after the fact.

This is apparently only one of many things you don't understand about statistics.

So, you admit, it's just cherry-picking.

No, of course I do not admit that it is just cherry picking.There are two ways you can tell that I do not admit that it is just cherry picking; which we might describe as the a priori and a posteriori methods. A posteriori, you can tell that I do not "admit it's just cherry-picking" because I have in fact never done so. A priori, one can deduce that I would not "admit it's just cherry-picking", because I am sane and do not say crazy things.

Then you agree that your emotional response (like mine) has no bearing on the reality of the situation.That is to say, wrong.

Hi Crash,I appreciate that you have a minor in mathematics, but there does seem to be something you're missing about statistics. You also don't seem to grasp the difference between real world data and ideal mathematical relationships. Instead of actually discussing anything you're maintaining a fusillade of false accusations about ecological fallacies and failure to understand derivatives and so on (and by the way I didn't define the origin as -1,-1, the software did that, I assume it rounded to the nearest integer, and if you really knew anything about statistics you wouldn't expect real world data to go through 0,0). As I said earlier, if that's to be your approach then I'll just leave you to it.To state the obvious even more clearly for your sake, mathematically in an ideal isolated region far from any crazed Canadians shooting Americans from across the border, 0 guns must correspond to 0 gun deaths. The line can only rise from there. You have no mechanism or data for the line reversing direction.--Percy

Well, another factor here is that the numbers come from many different years. 1994 to 2009 or so. So basically, we need more data from a consistent sample.See List of countries by firearm-related death rate - Wikipedia and Estimated number of civilian guns per capita by country - Wikipedia for the originals.But back to my point of removing obvious outliers - if statistical practice is to be followed, then the USA point must be thrown out of the analysis. But if the USA point is thrown out, then how can the result be used to analyze the USA situation?