Reader Comments

Post a new comment on this article


Posted by rafaerts on 11 Jun 2009 at 14:42 GMT

We found a significant positive relationship between perturbation magnitude and recovery time for variables that had fully recovered (Regression, r2 = 0.22, p<0.05, d.f. = 1, F = 6.3; Fig. 5). However, the significance was entirely determined by one strongly outlying point

The authors realized that the single outlier has such a tremendous leverage effect, and therefore it would have been better to have omitted this point, or to have omitted the whole regression.

No competing interests declared.

RE: Leverage

camille_couralet replied to rafaerts on 16 Jun 2009 at 15:30 GMT

Hi Raf,

yes I was also surprised and do not understand either. The figure is much less informative with this outliar.

Nice article though, the realistic and non-catastrophic viewpoint is very much appreciable.

No competing interests declared.