A basic fish-stock assessment system requires an integrated use of a model for the time evolution of a fish stock and information about the fish stock from catch data. Typical for common fish stock assess- ment systems has been the use of fairly simplistic data assimilation methodologies for the integration of observations with the dynamical models. On the other hand, there has been a fast development of assimilation techniques which can be used with highly nonlinear and complex dynamical models. In this paper some of these methods, which are based on Monte Carlo formulations, will be examined with a simple fish stock model. The methods used are the ensemble Kalman filter, the ensemble Kalman smoother and the simpler ensemble smoother.