canonical analysis of insulin data

The REG Procedure
Model: MODEL1
Multivariate Test 1

Error Matrix (E)
0.5400626855 9.0162268852
9.0162268852 3123.4273529

Hypothesis Matrix (H)
0.1881199232 0.7050774626
0.7050774626 51.724820999

  Canonical
Correlation		 Adjusted
Canonical
Correlation		 Approximate
Standard
Error		 Squared
Canonical
Correlation		 Eigenvalues of Inv(E)*H
= CanRsq/(1-CanRsq)		 Test of H0: The canonical correlations in the current row and all that follow are zero
  Eigenvalue Difference Proportion Cumulative Likelihood
Ratio		 Approximate
F Value		 Num DF Den DF Pr > F
1 0.514205 0.469242 0.109656 0.264407 0.3594 0.3434 0.9574 0.9574 0.72400963 2.39 6 82 0.0350
2 0.125488 0.047831 0.146724 0.015747 0.0160   0.0426 1.0000 0.98425273 0.34 2 42 0.7165

Multivariate Statistics and F Approximations
S=2 M=0 N=19.5
Statistic Value F Value Num DF Den DF Pr > F
Wilks' Lambda 0.72400963 2.39 6 82 0.0350
Pillai's Trace 0.28015406 2.28 6 84 0.0435
Hotelling-Lawley Trace 0.37544623 2.54 6 52.926 0.0312
Roy's Greatest Root 0.35944702 5.03 3 42 0.0045
NOTE: F Statistic for Roy's Greatest Root is an upper bound.
NOTE: F Statistic for Wilks' Lambda is exact.