ON THE USE OF DIVERGENCE STATISTICS TO MAKE INFERENCES ABOUT 3 HABITATS

Several coefficients, called divergences, have been suggested in the s tatistical literature to reflect the fact that some probability distri butions are ''closer together'' than others and consequently that it m ay be easier to distinguish between the distributions of one pair than between those of another. When comparing three biological populations , it is often interesting to measure how two of them ''move apart'' fr om the third. Deals with the statistical analysis of this problem by m eans of bivariate divergence statistics. Provides a unified study, dep icting the behaviour and relative merits of traditional divergences, b y using the (h,phi), divergence family of statistics introduced by Men endez et al.