The research problem here concerns the analytic determination of the distribution of demand during lead time for one of the standard inventory situations: the single item with stationary, probabilistic period demand and known distribution coupled with a stationary, probabilistic lead time with known distribution. It is assumed that period demand and lead time are independent variables. Alternative analytic routes and their tractability are discussed.
The work on determination of the distribution of demand during lead time and quantities such as protection level and expected back-order is summarized. This includes (i) cases where the distribution of demand during lead time has been fully characterized and (ii) cases where approximating distributions have been used to describe demand during lead time . The results are presented in tabular form for ease of reference.
The density function of the demand during lead time is derived when the period demand is Poisson distributed and the lead time is described by a normal variate restricted to non-negative values. If the non-negativity restriction on the normal variate is lifted, the demand during lead time is shown to follow the Hermite probability law under certain conditions. For this Hermite characterization, an expression for expected backorders is derived.