One of the puzzles of store-level scanner data is the lack of a dip in quantity sold in the weeks following a promotion. Such a dip is predicted by a consumer inventory model. During a promotion consumers buy more, not only for current consumption, but stockpile for future consumption. The predictions of such a model have been confirmed by household-level data yet seem harder to find in aggregate brand- or category-level data. We re-examine this puzzle and find two things. First, the effects at the household-level are present, but are much smaller than previously found. Our estimates are different because we control for household heterogeneity in a more general way than most previous work. This suggests that since the effects are small they might be harder to spot in aggregate data. Second, we show that the dip is present in the aggregate data, once we control for additional promotional activity, like feature and display. The latter has an opposing dynamic effect that masks the existence of the post promotion dip.