You are not currently logged in.
Access JSTOR through your library or other institution:
An Analysis of Diversity Using Rao's Quadratic Entropy
Tapan Kumar Nayak
Sankhyā: The Indian Journal of Statistics, Series B (1960-2002)
Vol. 48, No. 3 (Dec., 1986), pp. 315-330
Published by: Indian Statistical Institute
Stable URL: http://www.jstor.org/stable/25052456
Page Count: 16
You can always find the topics here!Topics: Entropy, Diversity indices, Eigenvalues, Matrices, Null hypothesis, Analysis of variance, Simulations, Logical givens, Criminals, Mathematical functions
Were these topics helpful?See something inaccurate? Let us know!
Select the topics that are inaccurate.
Preview not available
This paper generalizes the categorical analysis of variance (CATANOVA) methods of Light and Margolin (1971) and Anderson and Landis (1980, 1982) using Rao's quadratic entropy. This formulation permits greater flexibility in specifying pairwise category differences which vary according to substantive considerations. Based on the partitioning of the total diversity, measures of association are defined and interpreted as generalizations of Goodman and Kruskal's (1954) τ-measures. Using diversity decomposition, large sample tests for independence are developed and examined through simulation.
Sankhyā: The Indian Journal of Statistics, Series B (1960-2002) © 1986 Indian Statistical Institute