In many theoretical models, it is assumed that there are costs associa
ted with adjusting prices. In this paper, the existence, type, and mag
nitude of such costs are investigated empirically. A discrete-choice d
ynamic-programming model that nests fixed and variable costs is develo
ped, and econometric estimates of the adjustment-cost function are obt
ained. The data used to implement the model consist of weekly retail p
rices and sales of three brands of saltine crackers sold by four chain
s of grocery stores in a small U.S. town. The study has several distin
guishing characteristics. First, the data are highly disaggregate (at
the level of brand and store). Second, variables are sampled at weekly
intervals. Third, the model nests fixed-and variable-adjustment costs
and can therefore determine their relative importance. Finally, the d
iscrete-choice model is both structural and dynamic.