|
Abstract:
|
Inverse sampling procedures is considered to test k-variate multinomial models under multiple-decision theoretic point of view. A stopping rule is devised to satisfy a pre-determined P*-condition and to obtain corresponding sample sizes, whereas the Chi-squared test cannot provide. For developing the procedure, the incomplete Dirichlet integrals are primarily used to express the probability of correct decision, P{CD} for various configuration in multinomial models. It is also assumed that the probabilities of all k categories or cells (e.g., on a wheel of fortune) are at least ?(>0). For numerical studies Monte Carlo experiments are conducted, and for an illustration moderate cell configurations of a wheel of fortune will be considered as well.
|
