Working Paper: NBER ID: w1581
Authors: Kenneth D. West
Abstract: This paper develops and applies a novel test of the Holt, et al.(1961) linear quadratic inventory model. It is shown that a central property of the model is that a certain weighted sum of variances and covariances of production, sales and inventories must be nonnegative. The weights are the basic structural parameters of the model. The model may be tested by seeing whether this sum in fact is nonnegative. When the test is applied to some non-durables data aggregated to the two-digit SIC code level, it almost always rejects the model, even though the model does well by traditional criteria.
Keywords: Inventory Model; Production Smoothing; Variance Bounds Test
JEL Codes: E22; C13
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| nonnegativity of a weighted sum of variances and covariances of production, sales, and inventories (C69) | implications of the linear quadratic inventory model (C69) |
| expected cost savings from the optimal inventory policy should be nonnegative when compared to a static policy (C61) | optimal inventory policy (D25) |
| violation of the inequality (P37) | firms are not following the optimal inventory policy (L21) |
| violation of the inequality (P37) | increased costs (J32) |
| production smoothing does not solely motivate inventory holdings (D25) | other factors must be considered (F29) |