Homicides in NSW and gun control

Charles Scripter wrote:

[...regarding Tim Lambert's assertion of a significant decrease in homicide
in New South Wales in 1920, coincident with the enactment of a gun control
law in NSW in that same year...]

The Lambert analysis method
clearly shows that there was a significant decrease for any year one
may choose, from 1910 to 1930.

The statistical test shows that we can reject the null hypothesis of no
change in the homicide rate in NSW between 1910 and 1930. Because the
change is so highly significant, it also possible to reject the same
null hypothesis by putting a step at other years near 1920. Only
Charles Scripter could look at 20 statistical tests, all showing a
significant reduction in homicide, and conclude that there was no
reduction.

Chris BeHanna wrote:

Oh, come on, Tim! Talk about lying by telling half-truths! You
have repeatedly inferred in this forum that the "significant reduction" was
caused by the gun control law

I have never claimed that the reduction was definitely caused by the
gun law. Never. However, no other plausible explanation has been
offered. If you have one, please share it with us.

(or else why would you call out emphasis to the "significant
reduction" in 1920, when it can be clearly demonstrated that your
method shows a "significant reduction" for any year from 1910
through 1930?).

I'm sorry if you feel that comparing the situation before the gun law
with that after is somehow invalid. Perhaps you would share with us
the Behanna-approved methodology for evaluating the effects of a law?
You also persist in your misrepresentation of my "method". A test for
the significance of a reduction is not the same as a method for
estimating when the reduction occured. Despite being corrected on
this, you repeat the falsehood.

Charles's point, AND YOU KNOW IT, is simply that there is no possible
way that your statistical method can show or infer support for the hypothesis
that the NSW gun control law of 1920 was responsible for the "significant
reduction" of homicide during that same year.

Charles has repeatedly maintained that there was no significant
reduction in homicides in NSW. He has "supported" this contention by a
succession of bogus and erroneous arguments. His latest argument
seems to be that because he did 20 tests all showing a significant
reduction, that this somehow proves that there was no reduction.

It does you no credit to stick your head in the sand alongside his.

Now, having been caught in your half-truth/whole lie AGAIN, you
backpedal to this "null hypothesis" nonsense.

Do as all a favour: Go to the library, get a book on elementary
statistics, look up "null hypothesis", learn what it is, and come back
when you have a clue.

Tags

More like this

Could the changes be caused by noise? This calls for a t test, to see if the average homicide rate changed. Andy Freeman said: There's an interesting thing about averages. If you take the average of a declining series and compare it to the end point, you find that the average is, not surprisingly…
Your claim that I have not shown that the situations were stable is false. The homicide rate was roughly constant in the period before gun control and in the period after gun control. Andy Freeman said: The graphs have shown that it was roughly constant AFTER, but before.... there was a dip in…
My model has two parameters (pre 1920 rate, post 1920 rate). Your model has four parameters (starting rate, first decrease, second decrease, year that rate of decrease changed). The more parameters that your model has, the easier it is to fit the data. Frank Crary said: However, no one is…
In a previous posting I observed that the homicide rate in New South Wales fell dramatically following the introduction of gun controls in 1920. Here, again, is the graph showing the homicide rate in NSW from 1900-1977. (Vertical scale is homicide rate per 100 000 population) 3 * 2.8 2.6…