This paper develops a new method of identifying why current product unavailability has an effect on future brand choices. If the impact is solely due to changing preferences, then all competitors of the unavailable item gain proportionally to their share; if, however, there is lock-in, then the competitor that is chosen instead of the unavailable product should gain disproportionately more. Denial of service attacks at Yahoo, CNN, and Amazon show that unavailability has a medium-term impact. Lock-in drives 51% of the effect on Yahoo, but it dissipates much more quickly than the effect of changing preferences.