Skip to main content
. Author manuscript; available in PMC: 2012 Aug 9.
Published in final edited form as: Genet Epidemiol. 2011 May;35(4):211–216. doi: 10.1002/gepi.20567

Table 2.

Pearson’s correlations of the test statistics (Stat) or p-values (P) between KMR and GDBR based on 1000 simulations. In GDBR, we took the (centered) kernel matrix K as the initial similarity matrix S or as the centered similarity matrix G

Linear
 Quadratic
 IBS
 wIBS
OR GDBR Stat P Stat P Stat P Stat P
1 G = Kc .998 .995 .992 .992 .999 .995 .999 .995
S = K .903 .865 .903 .866 .969 .969 .969 .969
2 G = Kc .996 .995 .989 .994 .998 .995 .998 .995
S = K .960 .922 .952 .927 .992 .980 .993 .981