A Note on the Subdividsion of χ 2 into Components
- 1 June 1949
- journal article
- research article
- Published by JSTOR in Biometrika
- Vol. 36 (1/2) , 130-134
- https://doi.org/10.2307/2332536
Abstract
In an ( r x s) frequency table with observed frequencies aij and expected frequencies apij, where a =[image]> consider the matrix of [image] standardized variables, Xij -[long dash][plus or minus][long dash][long dash][long dash][long dash][plus or minus][long dash][center dot] The result 3 sppir of premultiplying this matrix by a Helmert matrix constructed from the row marginal values and postmultiplying by the transpose of the Helmert column matrix is an (r x s) matrix with zeroes in the 1st row and in the 1st column, while every other element is the value of X for a particular fourfold table related to the original (r x s) table.Keywords
This publication has 1 reference indexed in Scilit:
- On the Distribution of a Weighted Estimate of Variance and on Analysis of Variance in Certain Cases of Unequal WeightingJournal of the Royal Statistical Society, 1942