Once the semilandmarks have been slid as part of the GPA, they are then treated as ordinary landmarks - except that one will find that each semilandmark essentially adds just one rather than two dimensions to the shape space. This is not a problem in a PCA but requires some extra care in a CVA.
-------------------- F. James Rohlf, Distinguished Professor, Graduate Program Director Dept. Ecology & Evolution, Stony Brook University, Stony Brook, NY 11794-5345 Web: http://life.bio.sunysb.edu/ee/rohlf Morphometrics: http://life.bio.sunysb.edu/morph > -----Original Message----- > From: morphmet [mailto:[EMAIL PROTECTED] > Sent: Thursday, May 26, 2005 10:26 AM > To: morphmet > Subject: RE: Morphometric analysis > > Hi, > I have a question about the analysis of semi-landmarks. > Which is typically analysed after the thin-plate spline plus > registration routine? > A) The final coordinates of the semi-landmarks > analysed as if they started as regular landmarks, or > B) The distances, normal to the outlines, between the > final semi-landmarks and the outlines. > Best regards, > Ben > p.s. Have both been used? > > -----Original Message----- > From: morphmet [mailto:[EMAIL PROTECTED] > Sent: 26 May 2005 14:26 > To: morphmet > Subject: Re: Morphometric analysis > > > Dear Catherine, > > You should use the PW scores matrix in all subsequent > analyses of GM data using multivariate methods. > > By the way, your mollusk shells would provide an interesting > application for > > the still little explored "semilandmark" approach developed > by Fred Bookstein (and implemented by Jim Rohlf in the > TPSRelw program). > > Hope this helps. > > With best regards, > > On Thu, 26 May 2005 08:06:56 -0400, morphmet wrote > > > I'm a first year Ph.D student in the Ecology and Evolution > Department > > at Leeds University, England. I'm studying a cline in > morphotype in > > the inter tidal snail Littorina saxatilis which suggests > there may be > > speciation in progress. I am very interested in using geometric > > morphometrics to quantify the variation in shell shape of > the snails, > > although my knowledge of the field is limited at this stage. > > > > I have taken the route of landmarks and I am using the > software TPS. > > I plan to use PCA/DFA in an attempt to discriminate between the > > morphotypes. However, I am unsure whether to use the Partial warp > > scores matrix, Relative warps score matrix or Weight matrix > from the > > TPSRelw program in the analysis. > > > > I would be grateful for any advice. > > > > Catherine Sinfield > > -- > + - - - - - - - - - - - - Mauro J. Cavalcanti - - - - - - - - > - - - - + > | Programa de Pós-Graduação em Zoologia > | > | Museu Nacional/Universidade Federal do Rio de > Janeiro | > | Quinta da Boa Vista, 20940-040, Rio de Janeiro, RJ, > BRASIL | > | E-mail: [EMAIL PROTECTED] > | > | Web: http://maurobio.infobio.net > | > + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - > - - - - + > -- > Replies will be sent to the list. > For more information visit http://www.morphometrics.org > -- Replies will be sent to the list. For more information visit http://www.morphometrics.org
