Pardo Llorente, Julio Ángel2023-06-202023-06-201995-09-150096-300310.1016/0096-3003(94)00162-Whttps://hdl.handle.net/20.500.14352/57822The useful mutual information statistic is considered and its asymptotic properties are investigated either considering random sampling or stratified random sampling. Under different assumptions, it is shown that the asymptotic distribution of this statistic is either normal or a linear form in chi(2) variables. Finally, its application to testing hypotheses of independence in multinomial populations is given.engSome applications of the useful mutual informationjournal articlehttp://www.sciencedirect.com/science/article/pii/009630039400162Whttp://www.sciencedirect.comrestricted access519.22normal distributionlinear form in chi-squaresmutual information statisticrandom samplingstratified random samplingtesting hypotheses of independencemultinomial populationsEstadística matemática (Matemáticas)1209 Estadística