Open AccessA TEST OF INDEPENDENCE BASED ON THE $(r,s)$-DIRECTED DIVERGENCE
Author(s) -
Domingo Morales,
Leandro Pardo,
Miquel Salicrú,
Margarita Menéndez
Publication year - 1992
Publication title -
tamkang journal of mathematics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.324
H-Index - 18
eISSN - 0049-2930
pISSN - 2073-9826
DOI - 10.5556/j.tkjm.23.1992.4532
Subject(s) - mathematics , contingency table , divergence (linguistics) , independence (probability theory) , statistics , stratified sampling , sampling (signal processing) , measure (data warehouse) , random variable , product (mathematics) , joint probability distribution , econometrics , computer science , data mining , geometry , philosophy , linguistics , filter (signal processing) , computer vision
$(r,s)$-Directed divergence statistics quantifies the divergence between a joint probability measure and the product of its marginal prob abilities on the basis of contingency tables. Asymptotic properties of these statistics are investigated either considering random sampling or stratified random sampling with proportional allocation and indepen dence among strata. To finish some tests of hypotheses of independence are presented.