Explaining why cross-sectional data is not useful for comparing the impact of gun ownership on crime rates

I have made this point so many times, but it seems that people need this point made again.  I don't really expect much from the leftwing Center for American Progress, but they are again using purely cross-sectional data to make their claim that "Weak State Gun Laws" are associated with more gun violence.  Reuters and others have picked up on the claim without any attempt to talk to academics or others who might be critical.

Here are just two of paragraphs from my book The Bias Against Guns:

First, the cross-sectional studies: Suppose for the sake of argument that high-crime countries are the ones that most frequently adopt the most stringent gun control laws. Suppose further, for the sake of argument, that gun control indeed lowers crime, but not by enough to reduce rates to the same low levels prevailing in the majority of countries that did not adopt the laws. Looking across countries, it would then falsely appear that stricter gun control resulted in higher crime. Economists refer to this as an “endogeniety” problem. The adoption of the policy is a reaction to other events (that is, “endogenous”), in this case crime. To resolve this, one must examine how the high-crime areas that chose to adopt the controls changed over time —not only relative to their own past levels but also relative to areas that did not institute such controls. 

Unfortunately, many contemporary discussions rely on misinterpretations of cross-sectional data. The New York Times recently conducted a cross-sectional study of murder rates in states with and without the death penalty, and found that “Indeed, 10 of the 12 states without capital punishment have homicide rates below the national average, Federal Bureau of Investigation data shows, while half the states with the death penalty have homicide rates above the national average.” However, they erroneously concluded that the death penalty did not deter murder. The problem is that the states without the death penalty (Alaska, Hawaii, Iowa, Maine, Massachusetts, Michigan, Minnesota, North Dakota, Rhode Island, West Virginia, Wisconsin, and Vermont) have long enjoyed relatively low murder rates, something that might well have more to do with other factors than the death penalty. Instead one must compare, over time, how murder rates change in the two groups – those adopting the death penalty and those that did not.

Of course, there are times when cross-sectional data still shows more guns mean less crime (see also here), but that is still a wrong way to look at the data.  As I have described in my books More Guns, Less Crime and The Bias Against Guns, you need to use panel data.  When that is done the results clearly show more guns, less crime.

UPDATE: Ken Mauer emails me the following:

There was once a cholera epidemic in Russia. The government, in an effort to stem the disease, sent doctors to the worst-affected areas. The peasants of the province of S_____ discussed the situation and observed a very high correlation between the number of doctors in a given area and the incidence of cholera in that area (i.e. more doctors were observed in cholera areas than elsewhere). Relying on this hard fact, they rose and murdered their doctors.   

Franklin M. Fisher, The Identification Problem in Econometrics, (New York: McGraw-Hill, 1966) pp. 2-3.

Wealth per country and per person

Source: The Economist

Be careful of some claims that life is getting better for black males

All this seems pretty obvious to me, and it is hard to believe that people would measure the high-school drop out rate by not looking at the entire black population of that age group.  From the WSJ:

That has significant implications for evaluating the progress of black Americans, according to a book published this past week. The number of incarcerated Americans has grown far quicker than the general population, and today a large-enough portion of young black men are behind bars to skew findings by surveys that omit them, the author says. 

Among the generally accepted ideas about African-American young-male progress over the last three decades that Becky Pettit, a University of Washington sociologist, questions in her book "Invisible Men": that the high-school dropout rate has dropped precipitously; that employment rates for young high-school dropouts have stopped falling; and that the voter-turnout rate has gone up. . . .

MLive Media Group does an important investigation into data problems with justifiable homicide data

I have long been concerned about the problems with the FBI's justifiable homicide data, so it is nice to see John Barnes at MLive Media Group do a careful investigation of this data.  

Officially, there were 117 justifiable homicides involving civilians in Michigan from 2000 to 2010. Another 95 were killed by police, according to the statistics.
One reason those numbers are low is simple, MLive’s investigation found.
Police are reporting the cases as criminal homicides. When it’s later determined to be justifiable, they don’t change the easy-to-recode electronic records. It’s as simple as changing a “1” to a “4.”
That was the case in Kalamazoo County, where FBI statistics show only one justifiable homicide between 2000 and 2010. There were eight, three by civilians and five by police, MLive found.
“It’s all a data-input problem,” Kalamazoo Public Safety Chief Jeff Hadley said. “What happens is when the initial reports are generated, it’s coded as a homicide. It never gets recoded.” . . .

See also this piece from Monday. 

Cross country economic and social statistics to remember - Data

The OECD fact book has a lot of useful cross country data available here, though the latest data is only for 2010.

Sunspot data

The raw data on sunspot activity is available here. Some diagrams are available here. The raw data shows how clearly the recent sunspot activity has been suppressed.

An example of why it is so important to look at disaggregated data

Note that if some had looked at annual data, you would never have seen the pattern discussed in the WSJ article here.

If you are interested in seeing labor force data, this is where to go

The Bureau of Labor Statistics has very detailed data over many decades available here.