12.03.2014 Views

The Effects of Sanction Intensity on Criminal Conduct - JDAI Helpdesk

The Effects of Sanction Intensity on Criminal Conduct - JDAI Helpdesk

The Effects of Sanction Intensity on Criminal Conduct - JDAI Helpdesk

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

involved. Crimes that obviously met our definiti<strong>on</strong> included homicide, rape, assaults, and<br />

residential burglaries. Ars<strong>on</strong> was also included due to the high probability <str<strong>on</strong>g>of</str<strong>on</strong>g> costly<br />

damage, although it was not always possible to determine whether the <str<strong>on</strong>g>of</str<strong>on</strong>g>fense was<br />

committed against pers<strong>on</strong>al or commercial property.<br />

Some other <str<strong>on</strong>g>of</str<strong>on</strong>g>fenses in<br />

Pennsylvania (e.g., criminal mischief) have specific subsecti<strong>on</strong>s relating to different types<br />

<str<strong>on</strong>g>of</str<strong>on</strong>g> victims and these were classified as victim crimes where it was clear that pers<strong>on</strong>al<br />

victims were involved. Retail theft and some other acquisitive <str<strong>on</strong>g>of</str<strong>on</strong>g>fenses like theft <str<strong>on</strong>g>of</str<strong>on</strong>g><br />

services, which were most likely to involve corporate victims, were excluded. We also<br />

excluded ‘n<strong>on</strong>-permanent theft’ (unauthorized use <str<strong>on</strong>g>of</str<strong>on</strong>g>fenses) against any victim type.<br />

Analytic strategy<br />

We use straightforward tests to compare the prevalence (proporti<strong>on</strong> <str<strong>on</strong>g>of</str<strong>on</strong>g> <str<strong>on</strong>g>of</str<strong>on</strong>g>fenders<br />

involved in serious <str<strong>on</strong>g>of</str<strong>on</strong>g>fending) and frequency <str<strong>on</strong>g>of</str<strong>on</strong>g> serious <str<strong>on</strong>g>of</str<strong>on</strong>g>fending across groups.<br />

Frequencies are compared using a two-sample t-test for the difference between means.<br />

To assess prevalence, we examine the relative risk (risk ratio) <str<strong>on</strong>g>of</str<strong>on</strong>g> serious <str<strong>on</strong>g>of</str<strong>on</strong>g>fending<br />

between groups. <str<strong>on</strong>g>The</str<strong>on</strong>g> risk ratio is not <str<strong>on</strong>g>of</str<strong>on</strong>g>ten used in criminological research, but it is<br />

comm<strong>on</strong> in epidemiological research for analyzing dichotomous outcomes in cohort<br />

studies (in which known exposure/n<strong>on</strong>-exposure to a risk factor is cross-tabulated with<br />

disease/n<strong>on</strong>-disease status). It is simply a ratio <str<strong>on</strong>g>of</str<strong>on</strong>g> the probability (risk) <str<strong>on</strong>g>of</str<strong>on</strong>g> disease given<br />

exposure status, calculated by dividing the proporti<strong>on</strong> <str<strong>on</strong>g>of</str<strong>on</strong>g> subjects with the disease at <strong>on</strong>e<br />

level <str<strong>on</strong>g>of</str<strong>on</strong>g> exposure by the proporti<strong>on</strong> at the other level. As such, it is somewhat similar to<br />

an odds ratio, but has a c<strong>on</strong>siderably more intuitive interpretati<strong>on</strong>. 6<br />

Like the odds ratio,<br />

150

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!