[R] test of CA axis

Kris Lockyear k.lockyear at ucl.ac.uk
Thu Jul 5 20:02:51 CEST 2007

Dear All,

I am not a statistician, and was wondering if anyone could help me 
with the following.

Greenacre, in his Correspondence Analysis in Practice (1993, p.173) 
gives a method for testing the significance of an axis in CA where:

$\chi^2 = \lambda \times n$ where \lambda is the the eigenvalue for 
the principal axis and n is the number of objects in the 
analysis.  The value for \chi^2 is then compared to a table of 
critical values.  The table in his book is a subset of Table 51 in 
Pearson and Hartley 1976, Biometrica Tables for Statisticians vol II, 
described as "Percentage points of the extreme roots of 

Is there an easy way of doing this test in R?  My main problem in 
that Table 51 only gives values for a maximum of a p=10, \nu = 200 
table and mine are regularly much bigger than that (although it would 
be also nice to be able to put in the figures for lambda, n, p and 
\nu and get the probability back).

Many thanks in advance, Kris Lockyear.

Dr Kris Lockyear
Institute of Archaeology
31-34 Gordon Square

phone: 020 7679 4568
email: k.lockyear at ucl.ac.uk

More information about the R-help mailing list