The two pertinent rates – the number of firearms per capita versus the number of firearm-related fatalities per capita – correlate with a coefficient of -0.79744, indicating a strong, negative correlation between the two sets of data.
If you look at the raw numbers – the number of firearms, period, versus the number of firearm-related fatalities, or “gun deaths” – they correlate with a coefficient of -0.27315, which remains a negative correlation.
As always, correlation does not necessarily indicate, or even come close to proving, causality; but I am also not trying to prove causality. However, the notion of “more guns = more ‘gun deaths’” does try to claim causality, when there is absolutely no positive correlation to support such a causal link.
Therefore, the hypothesis of “more guns = more ‘gun deaths’” still cannot be true.
Jonathan
March 22, 2017
graphics matter, 2017 edition
[And this is why the anti-gun people have to lie. They should be arrested and prosecuted for conspiracy to deprive people of their rights.—Joe]
Hence the title of Lott’s famous book, “More guns, less crime”.
Meanwhile, something here doesn’t make any sense. If f(t) and g(t) have a correlation coefficient of -0.8, I would expect f(t)/c(t) and g(t)/c(t) — i.e., the same functions both multiplied (or divided) by the same number) to have the same correlation coefficient, rather than the drastically different value -0.27. Then again, I dropped out of Statistics 102, so I’m a bit challenged in this area…
The Pearson correlation coefficient (the most common measure of correlation; I assume he’s referring to that) isn’t a linear function. He’s not measuring f(t)/c(t), he’s measuring f(t/c); it wouldn’t be expected that they’re equal.
I am, indeed, using the Pearson coefficient.
Correlation is not causation, but causation *REQUIRES* correlation. If you’re going to claim that increased X causes increased Y, you have to show a correlation. If there isn’t one, your idea is worthless.