Responds to C. Hale and D. Sabbagh (see record 1994-25923-001) by noting that their critique's salience depends on whether one takes an annual unemployment series that contains a single historical spike as suitably represented either by the combination of a stationary series with a step function or as an I(1) (variables integrated of order one) series. The 1st alternative is equivalent to the assertion that the unemployment rate series is nonstationary in mean but not in variance, while the 2nd explanation is equivalent to the assertion that the series is nonstationary in variance and/or mean, depending on the specific I(1) model chosen. The authors reemphasize their point that if one accepts the structural model they proposed, it is difficult to identify both the positive and negative unemployment–crime effects with any prevailing set of measures and methods. (PsycINFO Database Record (c) 2016 APA, all rights reserved)