MEASURING NOISE IN INVENTORY MODELS

This paper has two purposes. One is to assess different models of inventory behavior in terms of their ability to approximate the realized data. We do this initially for the pure production smoothing model and then for a sequence of generalizations. Our analysis both performs specification tests as well as measures the deviations of the data from each null model through use of a noise ratio statistic. A second purpose is to explore whether observed cost shocks, in particular raw materials prices, help explain inventory movements. We find that the production smoothing model of inventories, augmented by buffer stock motives, stockout avoidance motives, and observed cost shocks, well approximates monthly data.