| Abstract [eng] |
We consider sampling designs, where inclusion (to sample) probabilities are mixtures of two components. The first component is proportional to the size of a population unit (described by means of an auxiliary information available). The second component is the same for every unit. We look for mixtures that minimize variances of various estimators of the population total and show how auxiliary information could help to find an approximate location of such mixtures. We report theoretical and simulation results in the case of Poisson samples drawn from populations which are generated by a linear regression model. |
