Bloomberg’s School of Public Health Cherry Picked Claim that firearm homicides in Connecticut fell 40% because of a gun licensing law

11 Jun , 2015  

Bloomberg School of Public Health Logo

The Bloomberg School of Public Health at Johns Hopkins University put out this press release on a paper by Rudolph, Stuart, Vernick, and Webster:

A 1995 Connecticut law requiring a permit or license – contingent on passing a background check – in order to purchase a handgun was associated with a 40 percent reduction in the state’s firearm-related homicide rate, new research suggests.

Researchers from the Johns Hopkins Center for Gun Policy and Research, part of the Johns Hopkins Bloomberg School of Public Health, compared Connecticut’s homicide rates during the 10 years following the law’s implementation to the rates that would have been expected had the law not been implemented. The large drop in homicides was found only in firearm-related killings, not in homicides by other means, as would be expected if the law drove the reduction.

The findings are published online June 11 in the American Journal of Public Health. . . .

Earlier research from Webster found that Missouri’s 2007 repeal of its handgun license law was associated with a 25 percent increase in its firearm homicide rates. . . .

It makes little sense to examine one state when ten states had have laws at least at some time requiring licensing (Hawaii, Illinois, Iowa, Missouri, Massachusetts, Michigan, Nebraska, New Jersey, New York, North Carolina, and the District of Columbia) and others have expanded background checks. Missouri and now Connecticut involves cherry picking.  The Missouri study is discussed here.  And Massachusetts serves as a strong example of why not all states are examined.  Connecticut serves as the strongest evidence that gun control advocates can point to but, as we will see, this evidence is very weak.

As the authors of the study note,  from 1995 to 2005 the firearm homicide rate in Connecticut indeed fell from 3.13 to 1.88 per 100,000 people, representing a 40% drop over a ten-year period (“We estimate that the law was associated with a 40% reduction in Connecticut’s firearm homicide rates during the first 10 years that the law was in place“).  However, unexplained is that the firearms homicide rate was falling even faster immediately prior to the licensing law.  From 1993 to 1995, the Connecticut firearms homicide rate fell from 4.5 to 3.13 per 100,000 residents, which means more than a 30% drop in just two years. This represented a greater decline than the 17% national decline over those two years.  Of course, Rudolph and his co-authors do not address this inconvenient fact (though if one looks at their Figure 1 on page 3 this preceding drop is clearly visible).

Their results are also extremely sensitive to the last year that they pick.  While it is true that Connecticut’s firearm homicide rate fell by 40% from 1995 to 2005, it only fell by 16% between 1995 and 2006 and 12.5% between 1995 and 2010.  Meanwhile the drops for the US and the rest of the Northeast are much greater.  From 1995 and 2006, the firearm homicide rates for the US and the rest of the Northeast fell respectively by 27% and 22%.  From 1995 and 2010, the drops were 39% and 31%.  The longer samples show a relative increase in Connecticut’s firearm homicide rate whether Rudolph et al. had looked at one additional year or five additional years.

The authors say that they limit the data to 2005 because one paper that they cite looked at only 10 years after a law that they were investigating (p. 4: “We conclude the post-law period in 2005 to limit extrapolation in our predictions of the counterfactual to 10 years, as has been done previously“).  But just because a study on to cigarette smoking looks at 12 years (not 10 as claimed (Proposition 99 went into effect on January 1, 1989 and their sample went until 2000)) after the law was in effect, doesn’t explain why a study on crime would do the same thing.  Indeed, the reason given by the authors that Rudolph et al. cite isn’t applicable to the current paper (p. 16: “It ends in 2000 because at about this time anti-tobacco measures were implemented across many states, invalidating them as potential control units“).  There was no similar adoption across the states of handgun licensing laws.  Yet, if Rudolph et al. had gone for this 12th year as the study that they cite does, it would have dramatically altered their results.

In three of the four years immediately after the law was passed in 1995, Connecticut’s firearm homicide rate rose relative to the firearm homicides in Northeastern States.  But there is no theory offered for why Connecticut’s firearm homicide rate would first rise relative to other Northeastern states, then fall relative to them for six years, and then rise relative to them for four of the next five years.

Connecticuts Firearm Homicides Relative to US NE

 

The same graph for next door Massachusetts shows how bad things were after their 1998 gun licensing law went into effect and why they picked Connecticut with all the arbitrary years that they examined.

Massachusetts Firearm Homicides Relative to US NE

The Webster study also cherry-picks what crime rates to look at.  For over all violent crimes as well as robbery and aggravated assault, Connecticut’s crime rate was falling relative to the rest of the US in the years prior to the licensing law and rising afterwards.  For murder, there is basically not change in trends before and after the licensing law.  While

Violent Crime CT

Murder CT

Rape CT

Robbery CT

Aggravated Assault CT

Here are the two states that  Rudolph et al claim are the best matches to create their synthetic Connecticut.  Just because there were some states that could be combined using historical data to match the changes in Connecticut’s doesn’t mean that you expect them to continue to predict future changes.  As a comparison, suppose that you found five stocks that when combined closely matched the changes in Apple stock over the last year, would you want to bet that those stocks would closely match changes in Apple’s stock over the next year?  Just because you had a historical relationship that matched the changes over the last year, it wouldn’t tell you very much what would happen next year.  The same thing with states, just because Nevada or California firearm homicides just happened to move with Connecticut’s over the years from 1984 to 1995, why you expect the political, police, economic, demographic, and other changes to cause their crime rates to change the same way from 1996 to 2005.

States used to create Synthetic Connecticut

Some simple regression results: looking at the trends in various crime rates before and after the Connecticut licensing law started. The regression results are available here.

UPDATE: Apparently timed with the release of the Bloomberg study, the two Connecticut US Senators and a couple of congressmen from other states have put out a bill in favor of national licensing of guns (see also here and here).

Instapundit

, , ,


30 Responses

  1. Brad says:

    Bloombergs a liar. Everyone already knows that.

  2. Ryle says:

    Thank you. 40% is such a ludicrous number to be attributed to a single law in a single state, I was surprised this got published. Now I know better.

  3. Bartosh Rudnicki says:

    I’m shocked Webster et al were able to go through peer-review procedure.

  4. gdnctr says:

    This is more libtard BS.
    Who commits 99% of gun-related crimes? CRIMINALS.
    Do criminals apply for permits and licenses? NO.
    Do criminals submit to background checks? NO
    Ergo, this festering, lying Bloomberg crap is CRAP.
    Johns Hopkins is scum for going along with the lies.

    • Deb says:

      Anyone who commits a crime is by definition a criminal, so 100% of gun-related CRIME is committed by CRIMINALS. However, gun-related suicides outnumber homicides by over 60%. In fact, guns are used in >50% of suicides. Then there’s the accidental deaths and those committed by family members, friends, neighbors, etc. So, even if background checks won’t stop the career criminals, they can stop some of the suicides, accidents, and would-be criminals. The less prevalent guns are, the less available they become and the less available they become, the less likely they will fall into the hands of career criminals.

  5. […] While firearms and crime researcher, John Lott, has already picked the study apart over at the Crime Prevention Research Center, I would like to take some time to discuss some of the shortcomings posed by this Bloomberg-funded […]

  6. Bartosh Rudnicki says:

    @gdnctr

    “Who commits 99% of gun-related crimes? CRIMINALS.”

    What’s your definition of being a criminal? Person with one arrest? And please show me some stats supporting your claim that 99% of gun-related crimes are comitted by those criminals.

  7. Bartosh Rudnicki says:

    Webster says:

    “A lot of the debate around guns has more to do with the culture, do you like or hate guns, and how do you interpret the Second Amendment. What’s important here is that a bill is introduced that is based on a foundation of scientific research showing this will save lives.”

    It’s amazing how Bloomberg can make up stats and research while pushing legislation at the same time.

  8. Dave Hardy says:

    How did it get past the editors and through peer review? It’s easy. This, and all of the questionable studies, were published in medical journals, not journals on criminology. Suppose that a criminology periodical decided, for some inexplicable reason, to accept an article claiming that adding lefunomide to Cisplatin chemo improved survival rates by 20%. The peer reviewers, criminologists, wouldn’t have the foggiest idea what was being argued, whether there were flaws in the methodology, or whether it accords with past results. So, a quick glance, nothing jumps out at me, vote for approval. Same here. I doubt most MDs would be familiar with homicide rate trends, or how the UCRs break down regions, and so on. So if it says rates fell, that must prove it worked.

  9. Bartosh Rudnicki says:

    Dave Hardy, you’ve reminded me of what Miguel A. Faria said, quote:

    “I was editor of the Journal of the Medical Association of Georgia in 1993. I was forced to resign my position because I insisted that BOTH sides of the gun control debate and research should be published in the medical literature. Many of my colleagues in leadership positions and associated with the AMA wanted us to publish papers and research with preordained conclusions that guns were bad and should be eradicated from the civilian population (…) During the late 1990s, I continued to evaluate the work of public health, but I could not get even my commentaries published in the mainstream medical journals because my conclusions did not necessarily agree with the predetermined judgment of reviewers”

    http://www.haciendapublishing.com/articles/gun-research-2013-%E2%80%94-interview-dr-miguel-faria-rebecca-trager-research-europe

  10. Bartosh Rudnicki says:

    John Lott, please check this out:

    1. Starting in 1995, Connecticut began expanding and deploying their state troopers into high crime areas, not just to catch criminals after the fact, but to crack down on drug dealers coming into the area and shooting the place up.

    http://articles.chicagotribune.com/1996-10-10/news/9610100250_1_drug-dealers-troopers-bridgeport

    2. Connecticut also, in that same period, began cracking down on both gang leaders and car theft rings, locking up career criminals in large numbers. And after only a year or so, that’s what they credited with cutting their murder rate in half.

    http://www.nytimes.com/1996/10/05/nyregion/in-bridgeport-stopping-cars-to-stop-a-wave-of-killings.html

  11. […] It’s like this stuff is driven by politics, not by the data. Related: Bloomberg’s School of Public Health Cherry Picked Claim that firearm homicides in Connecticut fell… […]

  12. […] it's a fraud: Bloomberg's School of Public Health Cherry Picked Claim that firearm homicides in Connecticut fell 4… All gun control is based on a lie. Remember the nonsense the Media was spewing about mass shooting […]

  13. countenance says:

    Earlier research from Webster found that Missouri’s 2007 repeal of its handgun license law was associated with a 25 percent increase in its firearm homicide rates. . . .

    And after that, a decrease, increase, decrease, increase, etc.

    The only way this “research” would have a point is if the “handgun license law,” i.e. the permit to transfer a concealable firearm paperwork, was ever enforced, in that someone who transferred a concealable firearm (“handgun”) was ever prosecuted for not doing the proper paperwork. As I had to do when I bought my first and thus far only pistol not long after my 21st birthday. However, I’ve known and talked to quite a few lawyers who deal or dealt with this part of the state law (when it existed), and they tell me that they never heard of a case where someone was so prosecuted.

  14. Brendan Perez says:

    Wait, I’ve been told repeatedly by gun control supporters that local and even state gun laws can’t be effective when all a person has to do is drive 30 minutes to another state and buy a gun due to their “lax” gun laws.

    It must be brutal sometimes for them, living with that much cognitive dissonance.

  15. […] An analysis conducted by John R. Lott, renowned economist and director of the Crime Prevention Research Center, indicates the study on Connecticut cited by the bill’s authors misrepresents the facts. “[U]nexplained,” Lott states, “is that the firearms homicide rate was falling even faster immediately prior to the licensing law.” Lott also accuses the researchers of cherry-picking their data. Lott notes: “To see … how sensitive the results are to the dates chosen, while it is true that Connecticut’s firearm homicide rate fell by 40% from 1995 to 2005, it only fell by 12.5% between 1995 and 2010.  Meanwhile from 1995 and 2010, the US firearm homicide rate fell by 39% and the Northeast firearm homicide rate fell by 31%.” […]

  16. jade_crayon says:

    From the single cited source (citation #9, Abadie et al.) this paper uses to justify the use of only a 10 year period. The actual reason Abadie et al. did 10-11 year time span is not some magical statistical signifiance of a 10 year period but rather (quote from the paper on effectiveness of anti-tobacco legislation is as follows):

    “We use annual state-level panel data for the period 1970– 2000. Proposition 99 was passed in November 1988 and went into effect in January 1989, giving us 19 years of pre-intervention data. Our sample period begins in 1970 because it is the first year for which data on cigarette sales are available for all our control states. It ends in 2000 because at about this time anti-tobacco measures were implemented across many states, invalidating them as potential control units. ”

    The Bloomberg study using this to claim “10 years is a good enough span” seems just too convenient, at best. A more cynical person might think they just wanted to justify ending the analysis period in 2005 (before homicide rates started climbing again) and hunted for any source that used a 10-year timespan, then cited it.

    Further, that study was about tobacco use. I don’t think many people would debate that everyone who buys tobacco intends to use it for its intended purpose (smoking it), and if you limit the chances to use it (making all restaurants no-smoking, etc., part of the laws in the cited study) then of course, tobacco use will drop (there are only 24 hours in a day to smoke) and then sales will go down. I don’t think a smoker who is cut off from smoking for an hour or two will make it up by smoking twice as much afterwards… Simple common sense.

    Simple common sense (which is not part of peer-review in certain fields, especially social “science”) tells us that the vast majority of people who buy guns plan on never using them for their first intended purpose, killing someone or threatening to do so. One could argue the only people who buy guns for their intended purpose (apart from sport shooting and hunting) are probably criminals who are not going through legal channels anyway.

    But the biggest red flags are the whole use of weighted averages to create the synthetic Connecticut by selectively using data from so many states (but not neighboring Massachusetts, which one would think should be a very close analogue in many facets) is just a playground for number fudging and cherry picking.

    At least they were honest in stating which states the cherry picked out of the data set, which is how they could pass peer-review, especially if the peers are also a pro gun-control.

  17. Christopher P. Corbett says:

    This is an outstanding organization. I’m of modest means but will contribute financially to the CPRC whenever possible. Thanks so much for your hard work and objective research!

  18. […] states in the Northeast.  Between 1998 and 2010, Massachusetts’s firearm homicide rate soared by 88 percent.  Michigan only recently gotten rid of its licensing law in December 2012, but firearm homicides […]

  19. […] was passed in 1995, although researchers including John Lott of the Crime Prevention Center have pointed out that shootings fell even faster in other nearby states that didn’t have the law during the same […]

  20. […] it was passed in 1995, although researchers including John Lott of the Crime Prevention Center have pointed out that shootings fell even faster in other nearby states that didn’t have the law during the same […]

  21. […] An analysis conducted by John R. Lott, renowned economist and director of the Crime Prevention Research Center, indicates the study on Connecticut cited by the bill’s authors misrepresents the facts. “[U]nexplained,” Lott states, “is that the firearms homicide rate was falling even faster immediately prior to the licensing law.” Lott also accuses the researchers of cherry-picking their data. Lott notes: “To see … how sensitive the results are to the dates chosen, while it is true that Connecticut’s firearm homicide rate fell by 40% from 1995 to 2005, it only fell by 12.5% between 1995 and 2010.  Meanwhile from 1995 and 2010, the US firearm homicide rate fell by 39% and the Northeast firearm homicide rate fell by 31%.” […]

  22. […] Some of those critiques above have been offered in some form by Robert Verbruggen at Real Clear Politics and John Lott at the Crime Prevention Research Center. […]

  23. […] Some of those critiques above have been offered in some form by Robert Verbruggen at Real Clear Politics and John Lott at the Crime Prevention Research Center. […]

  24. […] before Connecticut required the background checks.) Interesting graphs and analysis are here, here, here, […]

  25. […] I am for results, not talk Regards Pace here, for once… educate yourself before speaking. Bloomberg's School of Public Health Cherry Picked Claim that firearm homicides in Connecticut fell 4… As the authors of the study note, from 1995 to 2005 the firearm homicide rate in Connecticut […]

Leave a Reply

Your email address will not be published. Required fields are marked *