This post  prompted an e-mail exchange that caused me to re-read Donald Deere’s, Kevin Murphy’s, and Finis Welch’s excellent 1995 article in Regulation entitled “Sense and Nonsense on the Minimum Wage ” – which exposes many of the flaws in the Card-Krueger study. I find this analogy, from page 55, by Deere, Murphy, and Welch to be especially useful:
The baseline used [by Card and Krueger] to infer that employment rose after the minimum wage went up is calculated just before the higher minimum takes effect, and long after employers knew of the legislated increase. To conclude that the change in employment over this time frame gives a complete view of the minimum wage effect is like comparing the number of teenagers on the streets at 11:59 P.M. and 12:30 A.M. to measure the effect of a midnight curfew. Finding no difference does not mean that the curfew has no effect.