----- Forwarded message from [email protected] -----

Date: Wed, 5 Mar 2014 02:44:01 -0500
From: [email protected]
Reply-To: [email protected]
Subject: Re: Shape analysis without removing size as afactor?
To: [email protected]

The procrustes fit does remove size but doesn't take in to effect allometric scaling so you might want to maybe correct for this, (i.e. size correct) and see if it has an effect on your results. This will remove shape variation associated with age or size.

Its quite straight forward to do.

Under the covariation tab select regression

On the left hand side of the drop down tab select your data set (under dependent variables)
Under data matrices select procrustes coordinates
Under variables select procrustes coordinates

On the right hand side of the drop down tab select the same data set (under independent variables)
Under data matrices select centroid size
Under variable select centroid size (or log centroid size)

Tick the permutation box
Tick the pooled regression within subgroup box
High light the classifier for your subgroups in the box below this

Execute

No with your regression dataset highlighted generate a new covariance matrix using your regression residuals
Tick the pooled within-group covariance box and highlight your classifier again in the box underneath (what groups your comparing)

Execute

Now use the new covariance matrix for your PCA
Or use the regression residuals for your dicsriminant function / CVA

Hope this helps

Oliver Hooker
PR~Statistics


On 5 March 2014, [email protected] wrote:


----- Forwarded message from [email protected] -----

Date: Fri, 31 Jan 2014 20:33:52 -0800
From: [email protected]
Reply-To: [email protected]
Subject: Shape anal ysis without removing size as a factor?
To: [email protected]

----- Forwarded message from Celena Toon <[email protected]> -----

Date: Mon, 20 Jan 2014 15:36:52 -0500
From: Celena Toon <[email protected]>
Reply-To: Celena Toon <[email protected]>
Subject: Shape analysis without removing size as a factor?
To: [email protected]

Hello,

I've been working on my master's thesis that uses a geometric
morphometric approach to analyzing the human tibia and the _expression_
of sexual dimorphism. I've previously consulted this forum about
formatting my text file s and it has been a wonderful help! After
conducting my analyses, I did not get the results expected and my
advisor wants me to seek other ways I could potentially analyze my
data to cover all my bases and make sure I'm not doing something
wrong. Using MorphoJ, I conducted a Procrustes fit, a principal
components analysis, and a discriminant function analysis. I know
that the Procrustes fit removes size as a factor, but is there a way I
could analyze my data in terms of both size and shape? Or should I be
approaching this differently?

Thank you,
CT

----- End forwarded message -----

----- End forwarded message -----



----- End forwarded message -----



Reply via email to