Hi all!

I am a newcomer in the field of GM and have recently applied several GM 
tools for describing a new form across its developmental processes and 
analyzing the impact of infections on shape. 
For 8 successive days, I analyzed with MorphoJ (PCAs, DAs, etc) the change 
in shape that was induced by the treatment, versus the control group.

When sended the paper for revision, one Reviewer asked: 

"Are there any reasons why PCA analysis limitations (use of variance, 
linear projection) should not considered important in this analysis ? This 
kind of question should be addressed, because they are at the heart of any 
interesting question anyone would ask in performing such analysis : the 
relations between morphogenesis and variance. It seems unclear to me, after 
having read the article, why kernel PCA should not be privileged versus PCA. 

What is kernel PCA? Is it of standard use in GM? If not, what do you think 
the best answer should be?

(I used PCAs only to show differences between individuals and only relied 
on DAs for stating group differences at each one of the 8 successive days 

Thanks a lot!

MORPHMET may be accessed via its webpage at http://www.morphometrics.org
You received this message because you are subscribed to the Google Groups 
"MORPHMET" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to morphmet+unsubscr...@morphometrics.org.

Reply via email to