In this work we propose a fast algorithm for computing the exact small sam- pling distribution of a given statistic, when the population random variable is discrete. The algorithm relies on a recursion on block matrices that describes all possible random samples that can be generated. In this way, the power of modern programming which deÞnes objects in term of matrices is fully exploited for effective computations. Finally, some instances of applications are shown.
A fast algorithm for computing the sampling distribution of a statistic from discrete populations / Piccolo, Domenico. - In: QUADERNI DI STATISTICA. - ISSN 1594-3739. - STAMPA. - 7:(2005), pp. 91-105.
A fast algorithm for computing the sampling distribution of a statistic from discrete populations
PICCOLO, DOMENICO
2005
Abstract
In this work we propose a fast algorithm for computing the exact small sam- pling distribution of a given statistic, when the population random variable is discrete. The algorithm relies on a recursion on block matrices that describes all possible random samples that can be generated. In this way, the power of modern programming which deÞnes objects in term of matrices is fully exploited for effective computations. Finally, some instances of applications are shown.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
