This paper deals with decision making and its purpose is illustrated by the well known newsboy paradigm. In sec:The-newsboy-paradigm are restated the hypotheses and notations usually used (e.g. by Scarf 1958 [4]) and are recalled the elementary formulae for the best order quantity and the associated gain. Thereafter, in sec:Results-obtained-from, are compared different results that have been obtained when using different models: normal, lognormal, triangular and ``two Dirac's models''.
In sec:Discussion-about-hypotheses are discussed the hypotheses that were at the basis of these results. The fact is highlighted that actual measures can hardly provide sufficient knowledge to allow a direct application of these formulae. In reality, the knowledge we ever can have upon the probability distribution of the future demand is far lower than the limited knowledge we can have over the future demand itself. Therefore it is interesting to investigate how robust are the ``hints for an optimal order quantity'' we can extract from what we really know upon the future demand.
In sec:Max-min-problems, this problem is addressed by
the usual max-min method. For each order quantity 
, the worst
demand distribution among a given ``bucket of models'' is determined,
and thereafter the value of that maximize the ``gain in
the worst case'' is determined. The case of the triangular models
with given 
and 
is examined, and compared with the
general Scarf's solution (that uses ``two Dirac's models''). The
paper ends by some concluding remarks and a bibliography.