In this paper, we consider testing the hypothesis that all multinomial populations in the stratified contingency table are identically distributed against the alternative that all these popula- tions are in simple tre...In this paper, we consider testing the hypothesis that all multinomial populations in the stratified contingency table are identically distributed against the alternative that all these popula- tions are in simple tree order. We provide an asymptotic represen- tation of the order-restricted maximum likelihood estimate of the unknown parameters. The resulting estimators are proven to be ~n-consistent and asymptotically normal under appropriate conditions. A chi-squared test method is used for this hypothesis test problem. A real data set is applied to illustrate our theoretical result.展开更多
基金Supported by the National Natural Science Foundation of China (10771163)
文摘In this paper, we consider testing the hypothesis that all multinomial populations in the stratified contingency table are identically distributed against the alternative that all these popula- tions are in simple tree order. We provide an asymptotic represen- tation of the order-restricted maximum likelihood estimate of the unknown parameters. The resulting estimators are proven to be ~n-consistent and asymptotically normal under appropriate conditions. A chi-squared test method is used for this hypothesis test problem. A real data set is applied to illustrate our theoretical result.