In this post in my journey through Crime Analysis For Problem Solvers, we're covering Step 37 - Know That To Err Is Human.
I must admit that this was one of the harder chapters to write about, mainly because it is a technical discussion of how to measure prediction errors. In fact I don't think I have a whole to add by commenting on this chapter other than this one bit:
In some circumstances it is possible to use a pilot test to accurately estimate the errors by making the predictions, not acting on them, and carefully observing what happens. This might be difficult to do with offenders, who prefer to keep their misdeeds hidden, but it could work with potential victims or crime places. For example, a response to a problem might involve predicting which places are most likely to be crime sites and then intervening at those locations. Prior to implementing this response, a pilot study could be conducted in which the predictions are made, but no action is taken. If the error rates are unacceptably high, then it might not be worth implementing the response.It might be worth honing your analytical chops by making predictions about future criminal activity without any intervention. Hopefully you can work out any bugs in your analysis prior to committing resources to the problem.
Next time, I'll cover Step 38 - Embrace Your Key Role At Response