-------- Original Message --------
Subject:        PLS issues in MorphoJ
Date:   Mon, 16 May 2011 05:03:31 -0400
From:   <[email protected]>
To:     <[email protected]>



Dear all

I am encountering a problem in MorphoJ that I hope some of you may be
able to help me with. It is a rather complex story, so I hope I am able
to explain it clearly.

In some instances, when I perform a two-block partial least squares
analysis with regression residuals in block 1 and covariates in block 2,
MorphoJ does not give me the results. I know that it has done the
analysis, because it does give me the graphs and I can export the PLS
scores, but the results tab stays blank, so I do not have any
information on RV coefficient, p-value, etc. This does not happen for
all PLS analyses I do, just with some combinations of specimens and
covariates (four instances so far), and I have not been able to find out
what the problem is. As far as I can tell there is no single variable or
specimen that is included in the analyses that do not work, but excluded
from the analyses that do.

It does not seem to be the case that there is a mistake in the data
itself. I can do the analysis and get results with any part of the
covariates, just not all of them at the same time. If I use different
covariates it also works fine (one exception, see below). Sometimes I
can get results when using all covariates, but not all specimens, but
not always.

I do not think that dataset size could be the problem either. When I
perform a PLS analysis with the same covariates, but less specimens, the
problem remains in some instances, but not others. Additionally, I have
also done the same analysis on another dataset, which has the same
covariates, more specimens and more landmarks, and did not encounter the
problem then.

One specific subset of my specimens has problems with two completely
different sets covariates. Each of the specimens of this subset,
however, has also been used in other analyses without giving problems.

Has anybody encountered a similar problem? And were you able to fix it?
Any help is greatly appreciated, because I truly do not understand what
is going on here.

Best wishes,

Anneke van Heteren

(\\ _ ___ Anneke H. van Heteren

.-"`"(\\ _.""` `"-.

/ ` `-._ _.-" `\__

6 6) `-.__.-' Centre for Research in`", Evolutionary Anthropology

/ `;-` Department of Life Sciences

/ , | Roehampton* *University

() / /` | Whitelands* *College

`---`"~``\ | Holybourne Avenue

\ | London* *SW15 4JD

\ \ / / UNITED KINGDOM

/`, , | | /

/ "-.| | | /'

/ / | /,__ | /`\ [email protected]

/ /' | / `"'\ ( \ +44 (0) 20 8392 3728

__/ /' | | `\ \ \

\ / | | `\ \ \

`-,/ / | / |-"`

`"""^^^ `^^""""`


Consider the environment. Please don't print this e-mail unless you
really need to.

------------------------------------------------------------------------
This email and any attachments are confidential and intended solely for
the addressee and may also be privileged or exempt from disclosure under
applicable law. If you are not the addressee, or have received this
e-mail in error, please notify the sender immediately, delete it from
your system and do not copy, disclose or otherwise act upon any part of
this email or its attachments.

Internet communications are not guaranteed to be secure or virus-free.
Roehampton University does not accept responsibility for any loss
arising from unauthorised access to, or interference with, any Internet
communications by any third party, or from the transmission of any viruses.

Any opinion or other information in this e-mail or its attachments that
does not relate to the business of Roehampton University is personal to
the sender and is not given or endorsed by Roehampton University.

Roehampton University is a company limited by guarantee incorporated in
England under number 5161359. Registered Office: Grove House, Roehampton
Lane, London SW15 5PJ. An exempt charity.

Reply via email to