A stock/flow panel is a way of sampling a population of agents moving
through a collection of discrete states. The scheme is to form separat
e samples of the residents of each state - the stocks - and of those m
oving between states - the flows. We calculate optimal stock/flow samp
ling schemes and provide efficient estimators of the transition intens
ities in the particular case of an alternating Poisson process. We als
o compute the efficiency gains compared to randomly sampled panels.