Premium
Chisquare Tests From Clusters of Observations
Author(s) -
Helland Inge S.
Publication year - 1994
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710360705
Subject(s) - categorical variable , mathematics , statistics , correlation coefficient , correlation , simple (philosophy) , square (algebra) , multiple correlation , econometrics , geometry , philosophy , epistemology
A simple model for categorical observations that are correlated in clusters is developed. The implied correlation coefficient is used to define an effective number of observations, and a natural estimation procedure for the correlation coefficient is proposed. By grouping the clusters of observations, and by relating them to models of the probabilities for the implied categories, common chisquare tests are formulated and motivated asymptotically. As an example of applications we look at forage registrations for radio‐collared moose.