The interpretation of the “trend” model is slightly complicated, since the model already includes year effects to accommodate the time pattern of crime common across all counties. To see what this model does, consider a more flexible model with a series of separate dummy variables, for each number of years prior to—and following—the law change for adopting states (see the figures illustrating the section later in the chapter called “Extending the Baseline Specification to 2000”). Thus, for example, a variable called shall_issue_minus_1 is 1 if the observation corresponds to a county in a state that adopts the law in the following year, 0 otherwise. Similarly, shall_issue_plus_5 is 1 if the observation corresponds to a county in a state that adopted five years ago, 0 otherwise. And so on.

The coefficient on each of these variables shows how adopting states’ time patterns of crime rates move, relative to the national time pattern, surrounding the respective states’ law adoption. Note that the time pattern in question is not calendar time but rather time relative to local law adoption, which occurs in different calendar years in different places.

The trend model in equation 6.2 constrains the adopting states’ deviations to fall on two trend lines, one for years before and one for years after adoption. Thus, the model restricts the yearly movements in the deviations to fall on trend lines with break points at the time of law adoption.

STATISTICAL ANALYSES OF RIGHT-TO-CARRY LAWS

In this section, we review the basic empirical findings on the effects of right-to-carry laws. We begin with a discussion of Lott’s original estimates of Models 6.1 and 6.2 and the committee’s efforts to replicate these findings. We then discuss results from other studies that estimate the effects of right-to-carry laws on crime.

Lott’s Results

Table 6-1 (first row) displays Lott’s estimates from Model 6.1. Lott finds that where they have been adopted, right-to-carry laws have reduced homicide by about 8 percent, rapes by about 5 percent, and aggravated assaults by about 7 percent (Lott, 2000:51). Lott also finds that adoption of right-to-carry laws may increase the rates of nonviolent property crimes (burglary, larceny, auto theft). In theory, this is possible, as criminals substitute away from crimes that involve contact with victims toward crimes that do not involve encounters with victims.

Rows 2 and 3 of Table 6-1 report the results of the committee’s replication of these estimates. In row 2, we use the revised original data set and Lott’s computer programs. The committee was unable to replicate Lott’s estimate of the reduction in the murder rate, although the estimates are



The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement