On Optimization of Gaussian Process Observation

One result from the field of statistics of stochastic processes is received; it seems unexpected. As a rule a situation in mathematical statistics is following: more observations – more qualitative conclusions. Result, that is indicated, shows, that an opposite situations have been happened: the superfluous observations can turn out to be harmful. Note an once, that here we don’t mean a observations, requiring expences (the appropriate problems are well known and considered in the theory of optimal stopping moments). In our case the observations do not cost anything, but at the same time there is no reason to carry out superfluous ones. Furthermore our result has a practical meaning too.