Skip to content

reviewer comment

5 messages · John Kane, Mohamed Lajnef, S Ellison

Original
John Kane
# 
No idea of what sentence.  R-help strips any html and only provides a text message so all formatting has been lost.  I think the question is not really an R-help question but if you resubmit the post you need to show the sentence in question in another way.

John Kane
Kingston ON Canada
____________________________________________________________
GET FREE SMILEYS FOR YOUR IM & EMAIL - Learn more at http://www.inbox.com/smileys
Works with AIM?, MSN? Messenger, Yahoo!? Messenger, ICQ?, Google Talk? and most webmails
John Kane
# 
I think this is more a question for something like Cross Validated but you
   may well get a hint or two here.  Unfortunately while I vaguely see what the
   reviewer is getting at I certainly don't know enough to help.



   John Kane
   Kingston ON Canada

   -----Original Message-----
   From: mohamed.lajnef at inserm.fr
   Sent: Fri, 15 Mar 2013 14:38:10 +0100
   To: jrkrideau at inbox.com
   Subject: Re: [R] reviewer comment

   Thanks John for your reply.
   the  reviewer comment:
asymmetric distribution could affect Principal
Component Analysis results,  symmetry of distribution should be
tested. Authors should also indicate if outliers were observed and
consequently excluded because they could affect factors

My question: what does it mean asymmetry distribution could affect PCA  ? and a
lso outliers could affect factors?

sorry for this not R-help question.

Best regards 

M

   Le 15/03/13 14:05, John Kane a ?crit :

No idea of what sentence.  R-help strips any html and only provides a text mess
age so all formatting has been lost.  I think the question is not really an R-h
elp question but if you resubmit the post you need to show the sentence in ques
tion in another way.

John Kane
Kingston ON Canada


-----Original Message-----
From: [1]mohamed.lajnef at inserm.fr
Sent: Fri, 15 Mar 2013 11:26:45 +0100
To: [2]r-help at r-project.org
Subject: [R] reviewer comment

Could someone explain me this sentence reviewer below in blod underlined,

Authors should try to be more detailed in the description of analyses:
some of the details reported in the "Principal components analysis"
paragraph (Results) should be moved here.
Because a highly_/*asymmetric distribution could affect Principal
Component Analysis results,  symmetry of distribution should be
tested. Authors should also indicate if outliers were observed and
consequently excluded because they could affect factors*/_

Any help would be greatly appreciated!

Regards
ML

--
####################################
Mohamed Lajnef,IE INSERM U955 eq 15#
P?le de Psychiatrie                #
H?pital CHENEVIER                  #
40, rue Mesly                      #
94010 CRETEIL Cedex FRANCE         #
[3]Mohamed.lajnef at inserm.fr           #
tel : 01 49 81 32 79               #
Sec : 01 49 81 32 90               #
fax : 01 49 81 30 99               #
####################################



______________________________________________
[4]R-help at r-project.org mailing list
[5]https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
[6]http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

____________________________________________________________
GET FREE SMILEYS FOR YOUR IM & EMAIL - Learn more at [7]http://www.inbox.com/sm
ileys
Works with AIM?, MSN? Messenger, Yahoo!? Messenger, ICQ?, Google Talk? and most
 webmails



--
####################################
Mohamed Lajnef,IE INSERM U955 eq 15#
P?le de Psychiatrie                #
H?pital CHENEVIER                  #
40, rue Mesly                      #
94010 CRETEIL Cedex FRANCE         #
[8]Mohamed.lajnef at inserm.fr           #
tel : 01 49 81 32 79               #
Sec : 01 49 81 32 90               #
fax : 01 49 81 30 99               #
####################################
     _________________________________________________________________

   Free Online Photosharing - Share your photos online with your friends and
   family!
   Visit [9]http://www.inbox.com/photosharing to find out more!

References

   1. mailto:mohamed.lajnef at inserm.fr
   2. mailto:r-help at r-project.org
   3. mailto:Mohamed.lajnef at inserm.fr
   4. mailto:R-help at r-project.org
   5. https://stat.ethz.ch/mailman/listinfo/r-help
   6. http://www.R-project.org/posting-guide.html
   7. http://www.inbox.com/smileys
   8. mailto:Mohamed.lajnef at inserm.fr
   9. http://www.inbox.com/photosharing
S Ellison
# 
It means what it says. PCA will be affected by asymmetry  and outliers will affect the principal components (sometimes loosely called 'factors') In particular an extreme outlying data point can cause at least one PC to be essentially parallel to the vector between the outlier and the mean of the rest of the data. If you want a picture of factors describing the bulk of the data set, you need to chuck out the extreme points or use robust PCA.

Asymmetry I'd worry less about, at least for exploratory graphical presentation; if I had a nice spherical data set I'd probably not be very interested in the PCA because it'd not have much discriminatory power for groups. But inference based on things like mahalanobis distance often  relies on some sense of multivariate normality or the like, and if the model used for inference isn't built on a symmetric data set the inferences can be badly wrong. Think Turkish flag; the star is 'obviously' not part of the crescent, but in mahalanobis distance it's not much further from the (empty) centre of the crescent than most of the crescent is. 


*******************************************************************
This email and any attachments are confidential. Any use...{{dropped:8}}