Beruflich Dokumente
Kultur Dokumente
[Political Science]
Patricia G RAMBSCH
implications. Plausible arguments have been made for either re-
ductions or increases in violent crime due to these laws (Lott
The relationship between state murder rates and the liberal- and Mustard 1997). Proponents of the laws claim that shall-
ization of conditions under which a citizen can obtain a permit issue laws may deter crime if they increase concealed carry
to carry a concealed weapon (shall-issue laws) is controversial in public places. This in turn will increase the probability that
and important for policy. Many analyses have been done dur- the perpetrator’s intended victim would be armed. On the other
ing the last decade, but regression to the mean has been ignored hand (Ayres and Donohue 2003; Snyder 1997), opponents of the
with the exception of two papers which concluded that it did laws argue that they could encourage criminals to carry more
not matter. We consider state murder rates for 1976–2001 and powerful guns and discharge them more readily. Also, accessi-
compare relative murder rate slopes (relative to the U.S. murder ble guns could produce lethal consequences in otherwise minor
rate) for the five years following state adoption of shall-issue arguments. Finally, if shall-issue laws led to more guns in circu-
laws to the five years preceding for the 25 states becoming shall- lation, more guns would be available to criminals, because hun-
issue in 1981–1996. We find strong evidence for regression to dreds of thousands of guns are stolen yearly in the U.S. (Duggan
the mean. Using both a random and a fixed effects model, we 2001).
compare analyses ignoring the regression effect via a paired t- To provide context, Figure 1 shows the overall murder rate in
test to those controlling for it by conditioning on the pre shall- the 25 states that adopted shall issue laws between 1981 and
issue slopes. We find that controlling for regression to the mean 1996 and the overall murder rate in the remaining 25 states
changes the sign of the estimated intervention effect on mur- plus the District of Columbia. With the exception of Washing-
der rate slopes from negative to positive, has strong impact on ton (adopted 1960), New Hampshire (adopted before 1930), and
statistical significance, and gives no support to the hypothesis Vermont (no permit required), none of these states were shall-
that shall-issue laws have beneficial effects in reducing murder
rates.
KEY WORDS: Concealed carry; Homicide; Poisson regres- Table 1. Shall Issue States: name, year of shall-issue adoption, popu-
sion; Regression effect; Statistical regression. lation (millions) for that year, murder rate (number of murder victims
per 100,00 per year) averaged over the 11-year period from 5 years
before to 5 years after shall issue, and which of the four U.S. census
regions contained that state.
1. INTRODUCTION
Shall issue
State Year Popn. Murder rate Region
Recent decades have seen liberalization of state laws regard-
ing permits to carry concealed weapons, typically handguns, Alaska 1994 0.61 7.84 West
Arizona 1994 4.08 8.42 West
in public places. Before 1980, almost all states either forbade Arkansas 1995 2.48 9.38 South
civilian carry of concealed weapons (CCW) or granted permits Florida 1987 12.02 11.12 South
on a discretionary basis. In discretionary states, a local law en- Georgia 1989 6.44 11.29 South
forcement official must be convinced that the applicant has a Idaho 1990 1.01 3.02 West
Kentucky 1996 3.88 5.80 South
justifiable need for concealed carry and/or is of good charac- Louisiana 1996 4.35 15.64 South
ter. These terms are undefined in the law, leaving much latitude Maine 1981 1.13 2.46 Northeast
for discretion to the states. Between 1981 and 1996, 25 states Mississippi 1990 2.57 11.75 South
(Table 1) adopted shall-issue (SI) laws, requiring that anyone Montana 1991 0.81 3.36 West
Nevada 1995 1.53 10.48 West
meeting fairly objective criteria be issued a permit to carry a North Carolina 1995 7.20 9.39 South
concealed weapon. These criteria include a minimum age, typi- North Dakota 1985 0.69 1.29 Midwest
cally no prior felony conviction, no insanity, alcoholism or sub- Oklahoma 1995 3.28 7.39 South
Oregon 1989 2.82 4.91 West
stance abuse, not a fugitive from justice, and often completion Pennsylvania 1989 12.04 5.80 Northeast
of a firearm use and safety course or demonstration of firearm South Carolina 1996 3.70 8.51 South
competence. South Dakota 1985 0.71 2.11 Midwest
This article estimates the effect adoption of these laws had on Tennessee 1994 5.18 9.55 South
Texas 1995 18.72 9.76 South
murder rates, a controversial topic with important public health Utah 1995 1.95 2.87 West
Virginia 1995 6.62 7.62 South
Patricia Grambsch is Associate Professor, School of Public Health, Univer- West Virginia 1989 1.86 5.54 South
sity of Minnesota, 420 Delaware St. SE, Minneapolis, MN. 55455 (E-mail: Wyoming 1994 0.48 3.54 West
gramb001@tc.umn.edu).
c
2008 American Statistical Association DOI: 10.1198/000313008X362446 The American Statistician, November 2008, Vol. 62, No. 4 289
shall-issue could appear to reduce violent crime even if the two
are unrelated. In the foregoing research and commentary, such
a regression effect (regression to the mean) has been largely ig-
11
term regression to the mean. With ρ < 0, −Y1 < E[Y2 |Y1 ] <
µ, regression “through” the mean occurs. The generic term “re-
gression effect” encompasses both these cases. If selection on
Y1 makes Y1 ’s sample mean exceed µ, then on average Y2 ’s
5
7.5
horizontal, fluctuating, slightly increasing trend before law pas-
sage, followed by a precipitous drop with a nearly linear de-
crease after law passage. The average relative murder rate in-
0.90
implies that the big drop in the rate plot is an artifact of overall
7
Mean Murder Rate
trends. It also suggests a regression to the mean interpretation.
Shall issue laws were passed when the state’s murder rate had
0.85
6.5
0.80
Murder rate
Rel rate
3.1 Covariates
0.75
35
12
murders
murders
10
30
8
25
6
20
4
−4 −2 0 2 4 −4 −2 0 2 4
260
240
30
murders
murders
220
25
200
20
180
−4 −2 0 2 4 −4 −2 0 2 4
750
750
700
700
murders
murders
650
650
600
600
550
550
−4 −2 0 2 4 −4 −2 0 2 4
Figure A.1. Goodness-of-fit plots by quintiles of error. Fix method has solid lines; ran method has dashed lines.