Re: standard deviation of a slope

[Geoffrey Poole]

Geoffrey Poole wrote:
 >> Zar notes that the "standard error of estimate" (AKA "standard error
 >> of the regression") is a measure of the remaining variance in Y
 >> *after* taking into account the dependence of Y on X.

Bob O'Hara wrote:
 > Zar says that?  That's rubbish: the residual variance is the measure
 > of the remaining variance in Y after taking into account the
 > dependence of Y on X.

The way I read Zar, he starts with the regression residual sum of 
squares and divides degrees of freedom, which yields the variance of the 
residuals (to which you refer).  If you take the square root of this 
value, you get what Zar refers to as the "standard error of estimate."

I suppose I was not careful in my wording when I called this statistic a 
"measure of variance."  I should have said a "measure of variation."

Geoffrey Poole wrote:
 >> However, since the magnitude of this value is proportional to the
 >> magnitude of the dependent variable...

Bob O'Hara wrote:
 > Again, rubbish: add 20 000 to all of your Y's, and the variances will
 > all be the same.  The only difference is that the estimated intercept
 > is 20 000 higher.

Yes, adding a constant to a distribution will not change the variance. 
In thinking about it, it does seem confusing for Zar to state: "The 
magnitude of [the 'standard error of estimate'] is proportional to the 
magnitude of the dependent variable, Y." (top of page 335, Fourth 
Edition). But before we dismiss Zar (and Dapson) as rubbish, let's 
consider real-world data that represent biological phenomena rather than 
purely contrived data (e.g., adding a constant to all Y values).

Consider the weight of animals, for instance.  The variance in weight 
for a large-bodied species (say, humans) is much higher than for mice, 
and higher for mice than fleas.  Even within a single species (again, 
e.g., humans), the variance in weight among adults is far greater than 
among infants.  When considering regressions that predict the weight of 
individuals, then, it follows that the residuals of regressions are apt 
to increase in proportion to the average weight of individuals in the 
population.

Thus, couldn't biological factors (rather than any underlying 
mathematical formulation) drive a relationship between the "standard 
error of estimate" and the mean of the dependent variable?

-Geoff Poole

New DNR Job Opportunities

[DNRRecruiting DNRRecruiting]

The following are new opportunities that opened this week.  For details on 
these and other ongoing recruitment activities please visit the Employment page 
on DNR's Internet site:  http://www.dnr.wa.gov/jobs/ 
 

Silviculture Forester
Recruitment #2006-08-6862
Port Angeles, Wa
Closes: September 15


Timber Sales Compliance Forester
Recruitment #2006-08-3043
Sedro Woolley, WA
Closes:  August 30




 

Re: your mail

[Patina Mendez]

  This message is in MIME format.  The first part should be readable text,
  while the remaining parts are likely unreadable without MIME-aware tools.

---559023410-758783491-1155759868=:16574
Content-Type: TEXT/PLAIN; charset=X-UNKNOWN; format=flowed
Content-Transfer-Encoding: QUOTED-PRINTABLE

Hi Alison--

Drop an email to Riley Nelson at BYU ([EMAIL PROTECTED]).  He should be=
=20
able ot help you out.

--Tina Mendez

Patina Mendez
[EMAIL PROTECTED]
--
Div. Insect Biology
Dept. Env. Sci. Pol. & Mgmt.
University of California, Berkeley

302 Wellman Hall
Berkeley, CA 94720-3112
510.642.5913



On Wed, 16 Aug 2006, A Y wrote:

> Does any researcher and/or entomologist know the best methods of collecti=
ng
> adult Leuctra species (order Plecoptera) from streams?
> Thank you for your help
> Sincerely,
>
> ~Alison Yasick,
> PhD candidate
>
> Department of Biology, Geology and Environmental Science
> Cleveland State University
> 2121 Euclid Avenue
> Cleveland, OH 44115-2214
>
> The spirit of the eagle, and the courage of the wolf, be with you at all
> times.
>
> _
> FREE pop-up blocking with the new MSN Toolbar =96 get it now!
> http://toolbar.msn.click-url.com/go/onm00200415ave/direct/01/
>
---559023410-758783491-1155759868=:16574--

Forest Management Position at Michigan State

[Rich Kobe]

The Department of Forestry at Michigan State University seeks a full-time
(12 month) tenure-track, Assistant Professor of Forest Management (60%
research, 40% teaching). The position carries a 25% joint appointment in the
Department of Geography. We seek candidates who work at landscape or
regional scales with expertise in one or more of the following areas of
forest ecosystem management: landscape ecology, production forestry,
regional biogeochemistry, conservation biology, and human dimensions of
natural resource management. Application of geo-spatial analyses (e.g., GIS,
environmental modeling, remote sensing) in research and teaching is highly
desirable. The successful applicant will be expected to develop a nationally
recognized research program. Initial teaching responsibilities include a
senior-level course in Forest Management and a graduate course in the
candidate’s area of expertise. A Ph.D. is required by the time of
appointment. Publications in leading refereed journals, a successful record
of obtaining research grants, teaching experience, and demonstrated interest
in collaborative interdisciplinary research are desirable. Additional
information is available at: www.for.msu.edu/Position/ForMgt.htm. 

To ensure full consideration, please submit: curriculum vitae, statement of
research experience and future directions (2 pp max), statement of teaching
experience and philosophy (2 pp max), examples of publications, and 3
letters of reference by 30 September 2006 to: Richard Kobe, Chair, Forest
Management Search, Michigan State University, Department of Forestry, 126
Natural Resources Building, East Lansing, MI 48824-1222; email:
[EMAIL PROTECTED]; phone: (517) 355-8433. MSU is an Affirmative Action / Equal
Opportunity Employer.

Re: standard deviation of a slope

[Stephen B. Cox]

On 8/16/06, Anon. <[EMAIL PROTECTED]> wrote:
>
> Geoffrey Poole wrote:
> > Sarah:
> >
> > I think the reviewer comment has merit.
> >
> > I understand your problem as follows:  Your goal is to compare the
> > "usefulness" (not sure what you means by "usefulness", but we'll go wit=
h
> > it...) of a regressions across environmental conditions.  However, unde=
r
> > one set of environmental conditions the regression might be based on 10
> > points, but under another set of conditions, it might be based on 100
> > points.
> >
> > Unfortunately, even under the SAME environmental conditions, the SE of
> > the slope will decrease as the sample size increases.  Thus, if the
> > number of points varies across environmental conditions, you don't know
> > if changes in the SE of the slope are caused by differences in sample
> > size or differences in "usefulness" across conditions.
> >
> > In section 17.3 "Testing the significance of a regression" of Zar's
> > "Biostatistical Analysis" (pages 334-5 of forth edition) there is a clu=
e
> > that might help you with your dilemma...
> >
> > Zar notes that the "standard error of estimate" (AKA "standard error of
> > the regression") is a measure of the remaining variance in Y *after*
> > taking into account the dependence of Y on X.
> Zar says that?  That's rubbish: the residual variance is the measure of
> the remaining variance in Y after taking into account the dependence of
> Y on X.



Just to clear things up a bit... The terms "standard error of the estimate"
or "standard error of the regression" are used in Zar to represent the sqrt
of the residual variance.  They are not meant to be the same as the standar=
d
error of the slope.  However, the standard error of the slope  =3D standard
error of the estimate / sqrt(SSx),  where SSx is the sum of squares of X.



> However, since the
> > magnitude of this value is proportional to the magnitude of the
> > dependent variable,
> Again, rubbish: add 20 000 to all of your Y's, and the variances will
> all be the same.  The only difference is that the estimated intercept is
> 20 000 higher.


Bob is definetly correct here.  I suspect that what Zar is referring to her=
e
is that the standard error of the estimate is in the same units as the
dependent variable.  Hence, you can divide it by the mean to get a
"unitless" measure.



I might now have understood the original problem (possibly...).
>
> I think the idea is that in any single environment, one can regress two
> variables and get a fit etc.  But the question is: how well will this
> fit do in another environment?  The (actual) slope will probably be
> different between environments, and the more different they are, the
> less use it is to use the slope in one environment to predict in
> another.  The problem is the variation between the slopes in the
> different environments: obviously we can measure this variation by the
> standard deviation (or the variance!).
>
> In practice, I would suggest fitting a mixed model, where you allow the
> slope to vary randomly between environments.  Any decent stats package
> can do this: I think some people call them random regressions.  This
> will estimate the variation in slopes between environments, allowing for
> any differences in sample sizes in the different environments.  If the
> variance is small, then the predictions from one environment to another
> will be pretty good (obviously this depends a bit on the size of the
> regression coefficient: if it's zero, then there's no improvement anyway)=
.

I'll have to think a bit more about the best way of evaluating the
> importance of the variation in the slopes: the intuition is to ask how
> much better you do at predicting the value of a data point if you know
> which environment it was measured in, as compared to if it's a random
> environment.  Something similar to an intraclass correlation could be
> used.
>
> Incidentally, this is perhaps a good opportunity to plug this book:
> <
> http://www.stat.columbia.edu/~cook/movabletype/archives/2006/08/our_new_b=
ook_da.html
> >
> I read a draft in the spring and can heartily recommend it.  It covers
> the family of models that can be used for most statistical analyses I
> see in ecology (including the problem here!), in a practical way.

And now to bed.
>
> Bob
>
> --
> Bob O'Hara
> Department of Mathematics and Statistics
> P.O. Box 68 (Gustaf H=E4llstr=F6min katu 2b)
> FIN-00014 University of Helsinki
> Finland
>
> Telephone: +358-9-191 51479
> Mobile: +358 50 599 0540
> Fax:  +358-9-191 51400
> WWW:  http://www.RNI.Helsinki.FI/~boh/
> Journal of Negative Results - EEB: www.jnr-eeb.org
>


If Bob has indeed described the context of your question correctly, I would
second his suggestion of using a mixed model.  However, I realize nobody ha=
s
directly answered your original question.  I am not aware of a "standard
deviation of the slope" that is different from what most would call the
standard error of the slope.  A quick google

Re: Why not a law..Evolution

[DeSolla,Shane [Burlington]]

A law is not universally true.

Newtons laws of motion are universally false (though usually close
enough to be useful). And Newtons laws are not even close to being true
near the speed of light.

Laws describe phenomena; they don't require explanation.

Theories explain phenomena, even if they don't necessarily predict it
well.

Cheers,
Shane


Opinions expressed are those of the author and do not represent those of
his employer.



> -Original Message-
> From: Ecological Society of America: grants, jobs, news 
> [mailto:[EMAIL PROTECTED] On Behalf Of James J. Roper
> Sent: Wednesday, August 16, 2006 3:01 PM
> To: ECOLOG-L@LISTSERV.UMD.EDU
> Subject: Re: Why not a law..Evolution
> 
> But Malcolm,
> 
> It is not the "Theory of Evolution" that is the theory, but 
> rather the "Theory of Evolution BY NATURAL SELECTION" that is 
> the theory.  While most of us would agree that there is ample 
> proof, it should also be understood why it must be considered 
> a theory and not a law.  A law is universally true, while a 
> theory is provisionally true.  We all can imagine cases in 
> which some characteristic of an organism was due to genetic 
> drift or some other form of accident that favored a given 
> trait.  We can also remember th= e Spandrels of San Marcos 
> (Stephen J. Gould) and so recognize that we cannot call 
> everything we see a product of evolution by natural 
> selection,  If we do so, without proof, then we are making 
> assertions of faith.
> 
> So, until we prove that all features of living things are 
> adaptations that were formed by natural selectionthe 
> theory of evolution by natural selection remains just that.
> 
> But what a wonderful and explanative theory!
> 
> And we all KNOW that evolution happened, evolution is not a 
> theory, it is a fact, and not a law.
> 
> Cheers,
> 
> Jim
> 
> On 8/16/06, Malcolm McCallum <[EMAIL PROTECTED]> wrote:
> >
> > I wonder if it is time to stop calling it the "Theory of Evolution" 
> > and start calling it the "Law of Evolution,"  and to stop 
> referring to 
> > "evolutionary theory" and surplant that with "evolutionary law."
> >
> > Lets face it, there has to be more evidence for evolution 
> than there 
> > was for Gravity, etc. when they were moved to law status.
> >
> > Do we know of any case where organisms were not adapted by 
> or succumb 
> > to some outside force?
> >
> > Sounds like a law to me.
> >
> > VISIT HERPETOLOGICAL CONSERVATION AND BIOLOGY www.herpconbio.org < 
> > http://www.herpconbio.org> A New Journal Published in 
> Partnership with 
> > Partners in Amphibian and Reptile Conservation and the 
> World Congress 
> > of Herpetology.
> >
> > Malcolm L. McCallum
> > Assistant Professor
> > Department of Biological Sciences
> > Texas A&M University Texarkana
> > 2600 Robison Rd.
> > Texarkana, TX 75501
> > O: 1-903-223-3134
> > H: 1-903-791-3843
> > Homepage: https://www.eagle.tamut.edu/faculty/mmccallum/index.html
> >
> >
> > 
> >
> > From: Ecological Society of America: grants, jobs, news on 
> behalf of 
> > Ashwani Vasishth
> > Sent: Tue 8/15/2006 10:13 PM
> > To: ECOLOG-L@LISTSERV.UMD.EDU
> > Subject: Commentaries on science and on evolution
> >
> >
> >
> > There are two commentaries in the current issue of 
> Bioscience that I 
> > thought worth considering, in the particular context of the current 
> > "deba=
> te"
> > about the teaching of evolution science in our schools
> >
> > The first, by Ross H. Nehm, "Faith-based Evolution Education?" (638 
> > BioScience * August 2006 / Vol. 56 No. 8 
> www.biosciencemag.org) argues 
> > that scientists, generally defined, have limited themselves to 
> > generating belief statements on evolution, rather than 
> scientifically 
> > and systematically addressing the misconceptions inherent in lay 
> > beliefs and =
> in
> > creationist rhetoric.  In addition, we need to get much better at 
> > showing people why a knowledge of evolution science matters, to 
> > everyday folks, o=
> n
> > an everyday basis.
> >
> > The second, by Margaret Wertheim, "Who Is Science Writing 
> For?" (640 
> > BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org), 
> > argues that science writers, generally defined, are not positioning 
> > themselves where the readers are, in America, but rather 
> are catering 
> > to a very narr=
> ow
> > (and quite small) self-selecting cluster of individuals who 
> actively 
> > seek out science-related material.  We need to get better at doing 
> > what she ca=
> lls
> > "missionary work."
> >
> > Cheers,
> > -
> >   Ashwani
> >  Vasishth  [EMAIL PROTECTED]  (818) 677-6137
> >  Department of Urban Studies and Planning, ST 206
> > California State University, Northridge
> >  http://www.csun.edu/~vasishth/
> >
> 
> 
> 
> --=20
> -
> James J. Roper
> UFPR, Zoologia
> Caixa Postal 19034
> 81531-990 Curitiba, Paran=E1, Brasil
> =3D=3D=3D=3D=3D=

Re: Mark and Recapture of Turtles..../Xylene-based Paint

[J. Michael Nolan]

List Members

It was brought to our attention that one of the suggestions sent to us =
included the use of xylene-based paints. Below, have included the text =
from a citation saying this not a good practice with reptiles. Let us =
know if you want the original in pdf format.

Thanks for your time and also to Jim Boone from the Nevada State Museum =
for bringing this to everyone's attention.

Mike Nolansee below

One of your emails suggested using xylene-based paint to mark turtles.=20

I suggest you read our short note about

marking Side-blotched Lizards with xylene-based paint. The short version

is: it isn't a good idea.



This note was published in Herpetological Review, 30:33-34.


Effects of Marking Uta stansburiana (Sauria: Phrynosomatidae)

with Xylene-based Paint

JAMES L. BOONE and ELIZABETH A. LARUE

Nevada State Museum

700 Twin Lakes Drive, Las Vegas, NV 89107 U.S.A.

e-mail: jlboone @ aol.com

Population biologists often rely on marks to identify individual animals =
(Nietfeld et

al. 1994). For many years, herpetologists have marked reptiles with =
toe-clips, scale-clips,

and paint (Ferner 1979), and although any marks potentially affect =
animals, these generally

have been shown not to affect survival or other biological processes =
(e.g., Brown and Parker

1976; Jones and Ferguson 1980; Weatherhead et al. 1995). As technologies =
change, new

methods of marking appear. Some new methods obviously require testing =
before one can be

sure that the method does not adversely affect the target animal (e.g., =
glass beads, Fisher and

Muth 1989; radioactive tags, Pendleton 1956; PIT tags, Prior and =
Weatherhead 1996).

One example of a new method entering use without being tested was a =
modification

of standard painting techniques. Herpetologists have long used model =
paint (e.g., Testor

Corporation paints) to mark lizards and snakes without adverse effects =
(e.g., Jones and

Ferguson 1980). However, using model paint in the field can be messy and =
may require

researchers to carry and use paint thinner, leading one to look for more =
convenient methods.

Some researchers have used fingernail polish, while others have found =
quick-drying FaberCastel

T paint-pens more convenient for marking reptiles than either model =
paint or

fingernail polish. The carrier in these paint-pens, however, is xylene, =
and xylene has wellknown

toxic affects on animals (d'Azevedo et al. 1996; Rana and Kumar 1997). =
One might

assume that marking a reptile with a small amount of paint would result =
in a negligible dose

of xylene, especially in hot, arid environments where the paint dries =
almost immediately.

Based on this assumption, one might conclude that using paint-pens would =
not affect lizard

behavior, survival, or other demographic parameters. However, no one has =
tested this

assumption.

We conducted a pilot study to test the null hypothesis that xylene-based =
paint-pens

have no adverse affect on the survival of side-blotched lizards (Uta =
stansburiana), a small

insectivorous lizard that is common in the western U.S.A. and northern =
Mexico. We

captured 35 Uta (18 female; 17 male; 19 adults, snout-vent length, SVL > =
39 mm; 16

juveniles, SVL ? 39 mm) from five locations around southern Nevada =
(October, 1996

through October, 1997). We held the lizards in a lab and housed them on =
sand and gravel in

individual 2-liter jars. We exposed the lizards to ambient light and =
provided full-spectrum

lamps for heat during daylight hours. Daily ambient temperatures in the =
lab ranged from

about 13-27=B0C. Before marking the lizards, we kept them in captivity =
for 2-3 days to ensure

that no animals died immediately after capture.

We painted 21 lizards and used 14 as unpainted controls. We painted =
lizards in a

manner similar to how Uta had been marked during a mark-recapture study =
(Boone et al.

1998). We placed a spot of paint on the dorsum (diameter ? 1 cm, less =
than the width of the

dorsal surface) generally every 3-4 days until each lizard had been =
painted four times. This

simulated four capture-recapture events over two weeks using a =
day-specific color of paint

on each day of sampling. In the field, large spots (i.e., the width of =
the dorsum) were used

so that the paint color could be seen from a distance, presumably =
reducing stress on the

lizards by limiting the number of times that observers had to closely =
approach the animals

during exhaustive searches of 1-ha plots on each day of sampling. Each =
successive spot of

paint was placed on top of the previous spots. We recorded mortality and =
sleeping behavior

(i.e., spending the night above or below ground) for two weeks.

Of the 21 painted lizards, 5 died (4 juveniles, 1 adult; 24%), all of =
which had been

painted at least twice. No unpainted lizards died. While the sample size =
was small, the result

was statistically significant (Gadj =3D 5.408, P =3D 0.02). Sleeping =
behavior also chan

Re: Testing regression slopes for difference

[Stephen B. Cox]

Your approach is valid ONLY IF you are willing to ignore the fact that the
slope to which you are comparing your slope is itself an estimate.  That is
- you can use your CI to compare to a particular hypothesized value -
basically testing the hypothesis Ho: beta = beta_0, where beta_0 is some
hypothesized value, possibly from the literature.  However, if you really
want to see if two slopes are equal, say Ho: beta_1 = beta_2, you are better
off using the test on p. 360 of Zar.  This essentially looks at the CI of
the difference in slopes (b_1 - b_2) to see if it includes 0.

On 8/16/06, David Whitacre <[EMAIL PROTECTED]> wrote:
>
> While we're on regression--I know this is a really dumb question and I
> should know the answer. But here goes, my ignorance on display:
>
> In comparing some regressions to published ones, how do I test for
> significant difference in slope? I have calculated the 95% C.I. of my
> slope by using the t distribution applied to the SE of the slope, as
> described on p. 331 of Zar (1996, 3rd edition).
>
> If somebody else's slope is outside of this C.I., are the two slopes
> significantly different at p = 0.05? That is, I don't have to consider the
> C.I. on their slope?
>
> Thanks much for any enlightenment on this very basic issue.
>
> Dave W.
>

Re: standard deviation of a slope

[Stephen B. Cox]

On 8/16/06, David Bryant <[EMAIL PROTECTED]> wrote:
>
> Bob,
>
> I have a similar question to Sarah's and it may even be the same;
> I'm using orthogonal regression to determine the equivalence of two
> variables, both with errors.  I want to use the S.E. of the slope to
> compare to the optimum slope of one (equivalence among variable
> responses).  I contacted JMP (SAS institute) and they recommend the
> two-one-sided test (TOST)  which I understand as simply increasing
> the alpha to 0.10.  But this still gives a very large confidence
> interval providing a less than robust test.  In some instances a
> slope of 2 is not significantly different than slope of 1.  (!!??) In
> fact I have not found one instance in which the slopes differ.  This
> seems like a universal type II error to me.
>
> Can I use the standard test of homogeneity of slopes used in ANCOVA
> and compare to 1  (s.e. =3D0)  or would that lead to a type I error?


I would just look at the CI for your slope estimate and see if it included
1.



Thanks for your time,
>
> David
>
> David M Bryant Ph D
> University of New Hampshire
> Environmental Education Program
> Durham, NH 03824
>
> [EMAIL PROTECTED]
> 978-356-1928
>
>
>
> On Aug 16, 2006, at 9:39 AM, Anon. wrote:
>
> > Sarah Gilman wrote:
> >> Is it possible to calculate the standard deviation of the slope of a
> >> regression line and does anyone know how?  My best guess after
> >> reading several stats books is that the standard deviation and the
> >> standard error of the slope are different names for the same thing.
> >>
> > Technically, the standard error is the standard deviation of the
> > sampling distribution of a statistic, so it is the same as the
> > standard
> > deviation.  So, you're right.
> >
> >> The context of this question is  a manuscript comparing the
> >> usefulness of regression to estimate the slope of a relationship
> >> under different environmental conditions.  A reviewer suggested
> >> presenting the standard deviation of the slope rather than the
> >> standard error to compare the precision of the regression under
> >> different conditions.  For unrelated reasons, the sample sizes used
> >> in the compared regressions vary  from 10 to 200.  The reviewer
> >> argues that the sample size differences are influencing the standard
> >> error values, and so the standard deviation (which according to the
> >> reviewer doesn't incorporate the sample size) would be a more robust
> >> comparison of the precision of the slope estimate among these
> >> different regressions.
> >>
> > Well of course the sample sizes differences are influencing the
> > standard
> > error values!  And so they should: if you have a larger sample size,
> > then the estimates are more accurate.  Why would one want anything
> > other
> > than this to be the case?
> >
> > In some cases, standard errors are calculated by dividing a standard
> > deviation by sqrt(n), but these are only special cases.
> >
> > It may be that the reviewer can provide further enlightenment, but
> > from
> > what you've written, I'm not convinced that they have the right idea.
> >
> > Bob
> >
> > --
> > Bob O'Hara
> >
> > Dept. of Mathematics and Statistics
> > P.O. Box 68 (Gustaf H=84llstr"min katu 2b)
> > FIN-00014 University of Helsinki
> > Finland
> >
> > Telephone: +358-9-191 51479
> > Mobile: +358 50 599 0540
> > Fax:  +358-9-191 51400
> > WWW:  http://www.RNI.Helsinki.FI/~boh/
> > Journal of Negative Results - EEB: http://www.jnr-eeb.org
>

Research Associate Search: Hurricane Impacts on Forests

[Jeffrey Chambers]

Hurricane Impacts on Southeast Forests: The Department of Ecology and 
Evolutionary Biology, in the newly formed Division of Earth and Ecological 
Sciences at Tulane University, is seeking a post-doctoral or advanced post-
masters Research Associate.  The position is offered under a DOE funded 
National Institute for Climatic Change Research (NICCR) project 
entitled “Hurricane Impacts on Structure and Functioning of Southeastern 
Forests”, led by Dr. Jeffrey Chambers (http://www.tulane.edu/~jchamber/).  
The successful applicant will have significant experience in one or more 
of the following fields: forest field ecology, remote sensing, ecosystem 
simulation models, and GIS.  Job responsibilities will include 
participating in forest field campaigns to quantify species specific tree 
mortality and damage rates in coastal areas impacted by Major hurricanes.  
Additional activities in remote sensing, modeling, and GIS dependent on 
applicant’s skills.  Consideration of candidates will start immediately 
and continue until position is filled, with a 30 September 2006 target 
date.  Applicants are encouraged to respond immediately as the position 
will be filled when the appropriate candidate is found.  Salary negotiable 
based on qualifications of ~40k/year.  Applicants should send an 
electronic application with a statement of research interests, current CV, 
and contact information for three references to Jeff Chambers 
([EMAIL PROTECTED]) with NICCR Research Associate search in the subject 
line.

Faculty Position: Iowa State Univ. - Ecology & Evolution

[Dean Adams]

Ecology and Evolution of Organisms- Iowa State University, Ames
 
The Department of Ecology, Evolution, & Organismal Biology at Iowa State
University seeks a tenure-track Assistant Professor who excels in any area
compatible with our department’s interests in the ecology and evolution of
organisms. 
 
Potential research areas include:
form, function, and adaptation
plasticity, perceptory systems and behavior
population dynamics, species interactions, and ecological
organization
diversification and systematics. 
 
The successful candidate will join a dynamic department of 34 faculty who
use integrative approaches that bridge disciplines and span multiple levels
of biological organization. Applicants must have a Ph.D. in a biological
science and are expected to develop a nationally recognized research program
and contribute to undergraduate and graduate teaching. 
 
Submit cover letter, CV, 3 reprints, research & teaching statements, & 3
letters of recommendation electronically to: [EMAIL PROTECTED] by 15
Oct 2006  For more information and instructions, please see 
http://www.eeob.iastate.edu/search. Direct questions to Dr. Carol Vleck,
Search Committee Chair ([EMAIL PROTECTED]). 
 
The department is committed to fostering a culturally diverse educational
environment. ISU is an Equal Opportunity /Affirmative Action  Employer. 

Re: Why not a law..Evolution

[Aurora Toennisson/EPP/EXT/UTIA]

The way I was taught to define "Theory" and "Law," we can't call it a law.

A law is a description of a phenomenon that always happens (i.e. object
with mass with attract each other in proportion to their masses).  It
doesn't tell how or why it happens, just what happens.

A theory is an explaination of why or how something happens that is
supported by a large body of evidence (i.e. enstein's theory of gravity
that explains that gravity causes objects to attract because stuff with
mass bends space-time).

By these definitions, evolution is a theory, not a law.  The problem is
that most people use the term "theory" the way scientists use the word
"hypothesis".


Aurora Toennisson
[EMAIL PROTECTED]

Graduate Student
Entomology and Plant Pathology
205 Plant Science Building
2431 Joe Johnson Dr.
The University of Tennessee
Knoxville, TN 37996-4560

Lab Phone (865)974-5173
Office Phone (865)974-5367
Fax (865)974-8868

Re: Why not a law..Evolution

[James J. Roper]

But Malcolm,

It is not the "Theory of Evolution" that is the theory, but rather the
"Theory of Evolution BY NATURAL SELECTION" that is the theory.  While most
of us would agree that there is ample proof, it should also be understood
why it must be considered a theory and not a law.  A law is universally
true, while a theory is provisionally true.  We all can imagine cases in
which some characteristic of an organism was due to genetic drift or some
other form of accident that favored a given trait.  We can also remember th=
e
Spandrels of San Marcos (Stephen J. Gould) and so recognize that we cannot
call everything we see a product of evolution by natural selection,  If we
do so, without proof, then we are making assertions of faith.

So, until we prove that all features of living things are adaptations that
were formed by natural selectionthe theory of evolution by natural
selection remains just that.

But what a wonderful and explanative theory!

And we all KNOW that evolution happened, evolution is not a theory, it is a
fact, and not a law.

Cheers,

Jim

On 8/16/06, Malcolm McCallum <[EMAIL PROTECTED]> wrote:
>
> I wonder if it is time to stop calling it the "Theory of Evolution" and
> start calling it the "Law of Evolution,"  and to stop referring to
> "evolutionary theory" and surplant that with "evolutionary law."
>
> Lets face it, there has to be more evidence for evolution than there was
> for Gravity, etc. when they were moved to law status.
>
> Do we know of any case where organisms were not adapted by or succumb to
> some outside force?
>
> Sounds like a law to me.
>
> VISIT HERPETOLOGICAL CONSERVATION AND BIOLOGY www.herpconbio.org <
> http://www.herpconbio.org>
> A New Journal Published in Partnership with Partners in Amphibian and
> Reptile Conservation
> and the World Congress of Herpetology.
>
> Malcolm L. McCallum
> Assistant Professor
> Department of Biological Sciences
> Texas A&M University Texarkana
> 2600 Robison Rd.
> Texarkana, TX 75501
> O: 1-903-223-3134
> H: 1-903-791-3843
> Homepage: https://www.eagle.tamut.edu/faculty/mmccallum/index.html
>
>
> 
>
> From: Ecological Society of America: grants, jobs, news on behalf of
> Ashwani Vasishth
> Sent: Tue 8/15/2006 10:13 PM
> To: ECOLOG-L@LISTSERV.UMD.EDU
> Subject: Commentaries on science and on evolution
>
>
>
> There are two commentaries in the current issue of Bioscience that I
> thought worth considering, in the particular context of the current "deba=
te"
> about the teaching of evolution science in our schools
>
> The first, by Ross H. Nehm, "Faith-based Evolution Education?" (638
> BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org) argues
> that scientists, generally defined, have limited themselves to generating
> belief statements on evolution, rather than scientifically and
> systematically addressing the misconceptions inherent in lay beliefs and =
in
> creationist rhetoric.  In addition, we need to get much better at showing
> people why a knowledge of evolution science matters, to everyday folks, o=
n
> an everyday basis.
>
> The second, by Margaret Wertheim, "Who Is Science Writing For?" (640
> BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org), argues
> that science writers, generally defined, are not positioning themselves
> where the readers are, in America, but rather are catering to a very narr=
ow
> (and quite small) self-selecting cluster of individuals who actively seek
> out science-related material.  We need to get better at doing what she ca=
lls
> "missionary work."
>
> Cheers,
> -
>   Ashwani
>  Vasishth  [EMAIL PROTECTED]  (818) 677-6137
>  Department of Urban Studies and Planning, ST 206
> California State University, Northridge
>  http://www.csun.edu/~vasishth/
>



--=20
-
James J. Roper
UFPR, Zoologia
Caixa Postal 19034
81531-990 Curitiba, Paran=E1, Brasil
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D
E-mail:[EMAIL PROTECTED]
Phone/Fone/Tel=E9fono: 55 41 33611764
celular:55 41 99870543
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D
Ecologia e Conserva=E7=E3o na UFPR
http://www.bio.ufpr.br/ecologia/
-
http://jjroper.sites.uol.com.br

Testing regression slopes for difference

[David Whitacre]

While we're on regression--I know this is a really dumb question and I =
should know the answer. But here goes, my ignorance on display:

In comparing some regressions to published ones, how do I test for =
significant difference in slope? I have calculated the 95% C.I. of my =
slope by using the t distribution applied to the SE of the slope, as =
described on p. 331 of Zar (1996, 3rd edition).

If somebody else's slope is outside of this C.I., are the two slopes =
significantly different at p =3D 0.05? That is, I don't have to consider =
the C.I. on their slope?

Thanks much for any enlightenment on this very basic issue.

Dave W.

Re: standard deviation of a slope

[Anon.]

Geoffrey Poole wrote:
> Sarah:
>
> I think the reviewer comment has merit.
>
> I understand your problem as follows:  Your goal is to compare the 
> "usefulness" (not sure what you means by "usefulness", but we'll go with 
> it...) of a regressions across environmental conditions.  However, under 
> one set of environmental conditions the regression might be based on 10 
> points, but under another set of conditions, it might be based on 100 
> points.
>
> Unfortunately, even under the SAME environmental conditions, the SE of 
> the slope will decrease as the sample size increases.  Thus, if the 
> number of points varies across environmental conditions, you don't know 
> if changes in the SE of the slope are caused by differences in sample 
> size or differences in "usefulness" across conditions.
>
> In section 17.3 "Testing the significance of a regression" of Zar's 
> "Biostatistical Analysis" (pages 334-5 of forth edition) there is a clue 
> that might help you with your dilemma...
>
> Zar notes that the "standard error of estimate" (AKA "standard error of 
> the regression") is a measure of the remaining variance in Y *after* 
> taking into account the dependence of Y on X.  
Zar says that?  That's rubbish: the residual variance is the measure of 
the remaining variance in Y after taking into account the dependence of 
Y on X.

> However, since the 
> magnitude of this value is proportional to the magnitude of the 
> dependent variable, 
Again, rubbish: add 20 000 to all of your Y's, and the variances will 
all be the same.  The only difference is that the estimated intercept is 
20 000 higher.

I might now have understood the original problem (possibly...).

I think the idea is that in any single environment, one can regress two 
variables and get a fit etc.  But the question is: how well will this 
fit do in another environment?  The (actual) slope will probably be 
different between environments, and the more different they are, the 
less use it is to use the slope in one environment to predict in 
another.  The problem is the variation between the slopes in the 
different environments: obviously we can measure this variation by the 
standard deviation (or the variance!).

In practice, I would suggest fitting a mixed model, where you allow the 
slope to vary randomly between environments.  Any decent stats package 
can do this: I think some people call them random regressions.  This 
will estimate the variation in slopes between environments, allowing for 
any differences in sample sizes in the different environments.  If the 
variance is small, then the predictions from one environment to another 
will be pretty good (obviously this depends a bit on the size of the 
regression coefficient: if it's zero, then there's no improvement anyway).

I'll have to think a bit more about the best way of evaluating the 
importance of the variation in the slopes: the intuition is to ask how 
much better you do at predicting the value of a data point if you know 
which environment it was measured in, as compared to if it's a random 
environment.  Something similar to an intraclass correlation could be used.

Incidentally, this is perhaps a good opportunity to plug this book:

I read a draft in the spring and can heartily recommend it.  It covers 
the family of models that can be used for most statistical analyses I 
see in ecology (including the problem here!), in a practical way.

And now to bed.

Bob

-- 
Bob O'Hara
Department of Mathematics and Statistics
P.O. Box 68 (Gustaf Hällströmin katu 2b)
FIN-00014 University of Helsinki
Finland

Telephone: +358-9-191 51479
Mobile: +358 50 599 0540
Fax:  +358-9-191 51400
WWW:  http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results - EEB: www.jnr-eeb.org

Re: Mark and Recapture of Turtles....

[J. Michael Nolan]

One more

Mike Nolan

Four  ways to ID turtles for mark/recapture are ; 1) place the turtle on =
a fllat bed  scanner to enter unique marking images into a computer for =
future recapture comparasions. 2) Compare digital photographs upon each =
recapture.
3) before computers, turtles were simply xerox copied on a copier  to =
compare with future recaptures.
 4) A digital ( dots per square inch) laser scanner in the newest ,and =
most expensive rage to read the unique pits and grooves and markings on =
animal skin to identify individuals.  There are other non invasive high =
tech scanning methods to accomplish your goals but they can get very =
expensive. GOOD LUCK!=20

Call weekdays, evenings and weekends. Leave your phone number/best time =
to return your call and/or your e-mail address if we are on another line =
or away from our phones.=20

Sincerely,

J. Michael Nolan, Director
=20
Rainforest and Reef 501 (c)(3) non-profit

*=
*
"Outstanding-Affordable Field Courses in Rainforest & Marine Ecology"

"Spanish Immersion offered in Mexico, Costa Rica,=20
Nicaragua, Panama, Bolivia, Ecuador and Peru"
Web: http://iwanttolearnspanish.org (being updated for 07)

U.S. Office:
Rainforest and Reef 501 (c)(3) non-profit
P.O. Box 141543
Grand Rapids, Michigan 49514-1543 USA
Phone: 1.616.604.0546=20
Toll Free: 1.877.255.3721
Skype Phone: mikenolan1
Live Chat and Phone MS Live Messenger: [EMAIL PROTECTED]
E-mail: [EMAIL PROTECTED] or [EMAIL PROTECTED]
Web: http://www.rainforestandreef.org (being updated for 07)

Latin America Office:
P.O. Box 850-1150
San Jos=E9, Costa Rica, Central America
Att: Juan Pablo Bello C.
Program Director, Latin America
Phone: 011.506.290.8883/011.506.822.8222 (Cell)/Fax: 011.506.290.8883
E-mail: [EMAIL PROTECTED]
*=
*

Re: Why not a law..Evolution

[Robert Hamilton]

I guess you could have a law that things evolve, but what we look at as
a theory of evolution is too complex for a concept as simple as a "law".
The problem we have with any theory is the issue of what is a theory,
especially the nonsense hypothetico-deductive "model" presented in high
school and freshman textbooks.

You have a "Law of Gravity", but that lacks any real connection to the
theory that explains why it is so. Thus a "Law of Evolution" is fine,
but it cannot replace theory as to why it is so, or it's consequences.
We certainly seem to know a lot more about why evolution happens than
why we have gravity.

Rob Hamilton

"So easy it seemed once found, which yet
unfound most would have thought impossible"

John Milton


Robert G. Hamilton
Department of Biological Sciences
Mississippi College
P.O. Box 4045
200 South Capitol Street
Clinton, MS 39058
Phone: (601) 925-3872 
FAX (601) 925-3978

>>> Malcolm McCallum <[EMAIL PROTECTED]> 8/16/2006 8:56 AM
>>>
I wonder if it is time to stop calling it the "Theory of Evolution" and
=
start calling it the "Law of Evolution,"  and to stop referring to =
"evolutionary theory" and surplant that with "evolutionary law."=20
=20
Lets face it, there has to be more evidence for evolution than there
was =
for Gravity, etc. when they were moved to law status.
=20
Do we know of any case where organisms were not adapted by or succumb
to =
some outside force? =20
=20
Sounds like a law to me. =20
=20
VISIT HERPETOLOGICAL CONSERVATION AND BIOLOGY www.herpconbio.org =
=20
A New Journal Published in Partnership with Partners in Amphibian and
=
Reptile Conservation
and the World Congress of Herpetology.
=20
Malcolm L. McCallum
Assistant Professor
Department of Biological Sciences
Texas A&M University Texarkana
2600 Robison Rd.
Texarkana, TX 75501
O: 1-903-223-3134
H: 1-903-791-3843
Homepage: https://www.eagle.tamut.edu/faculty/mmccallum/index.html 
=20



From: Ecological Society of America: grants, jobs, news on behalf of =
Ashwani Vasishth
Sent: Tue 8/15/2006 10:13 PM
To: ECOLOG-L@LISTSERV.UMD.EDU 
Subject: Commentaries on science and on evolution



There are two commentaries in the current issue of Bioscience that I =
thought worth considering, in the particular context of the current =
"debate" about the teaching of evolution science in our schools

The first, by Ross H. Nehm, "Faith-based Evolution Education?" (638 =
BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org) argues
=
that scientists, generally defined, have limited themselves to =
generating belief statements on evolution, rather than scientifically
=
and systematically addressing the misconceptions inherent in lay
beliefs =
and in creationist rhetoric.  In addition, we need to get much better
at =
showing people why a knowledge of evolution science matters, to
everyday =
folks, on an everyday basis.

The second, by Margaret Wertheim, "Who Is Science Writing For?" (640 =
BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org), argues
=
that science writers, generally defined, are not positioning themselves
=
where the readers are, in America, but rather are catering to a very =
narrow (and quite small) self-selecting cluster of individuals who =
actively seek out science-related material.  We need to get better at
=
doing what she calls "missionary work."

Cheers,
-
  Ashwani
 Vasishth  [EMAIL PROTECTED]  (818) 677-6137
 Department of Urban Studies and Planning, ST 206
California State University, Northridge
 http://www.csun.edu/~vasishth/

[no subject]

[A Y]

Does any researcher and/or entomologist know the best methods of collecting 
adult Leuctra species (order Plecoptera) from streams?
Thank you for your help
Sincerely,

~Alison Yasick,
PhD candidate

Department of Biology, Geology and Environmental Science
Cleveland State University
2121 Euclid Avenue
Cleveland, OH 44115-2214

The spirit of the eagle, and the courage of the wolf, be with you at all 
times.

_
FREE pop-up blocking with the new MSN Toolbar – get it now! 
http://toolbar.msn.click-url.com/go/onm00200415ave/direct/01/

Re: Mark and Recapture of Turtles....

[J. Michael Nolan]

A summary of responses. Thank you for all the participation and =
apologies for the formatting. I tried to paste an image of a turtles =
plastron and a recommended notching technique. There is a citation for =
it below, if you want the actual image contact me directly.

Mike Nolan

I would think some paint would work fine in the short term for turtles -
they would have to be held long enough to let it dry - a blow dryer
helps.. :)

They could also use different colors or paint spots on different areas
of the carapace to identify individuals - it would be a cool lab =
project.

You can use a standard drill to drill tiny holes in one or more marginal =

scutes, using either an established or a custom code for naming these=20
marginal scutes.

For closed populations, yes.  Variations of Jolly-Seber or=20
Cormack-Jolly-Seber for open pops.

I mark freshwater mussels all the time and I think that our method is
relatively un-invasive.  We use superglue and floy tags.  You could use
any small coded plastic object (even color-coded plastic beads) and glue
to an area of the shell that is unlikely to cause the turtle harm (not
sure what to suggest there).  My collaborator's tags have stayed on for
longer than 8 years.  If you are just trying to get a simple
Lincoln-Peterson estimate, you won't need long-term marks; just marks =
that
will stay on long enough to satisfy assumptions of the estimate. =20

Turtles can be notched with using a small triangular file to file a =20
notch in the shell. For a one time study of a small group of turtles, =20
you can easily set up a code system making use of the 22 to 24 marginal  =

scutes on the turtle's carapace. Turtles usually have 12 marginals on =20
the right and left side. Just file deeply enough to make a mark that is  =

1-2 mm deep. This causes only temporary annoyance to the turtle and =20
does not cause any serious pain. Notching is a standard method, =20
developed in the 30s. The marks will actually last for years, depending  =

on the age of the turtle.

I was in Honduras this past june where they are doing mark/recapture of =
Hawskbills and Green Sea Turtles.=20

I believe they used a dremel tool to engrave the # in the carapace, =
filled the grooves with white out and then sealed it with enamel (nail =
or otherwise). It seemed that paint alone was not good enough, and if =
you don't want to tag a flipper... the little guys get a turtle tattoo =
of sorts.=20

In case you would like to get more info, turtle waiting pool is at =
www.reefhouseresort.com  look for the TAPS link at the bottom of the =
page.=20

Have seen nail polish put to good uses in cases like this, even with =
beetles, etc.  Not sur eabout how "weather proof" it is however.

We have had success with the following method for tagging Asian shore =
crabs in salt water. Get some waterproof paper. (Ward's sells it). Print =
out your numbers or letters for tagging on the waterproof paper using a =
laser (not inkjet) printer. Once the turtle shell is dry, attach the tag =
using clear nail polish. I'll be very interested to hear how this works =
for you and what others can suggest.=20

I would look at those small cordless dremel tools they sell at hardware=20
stores. A small engraving tip would work well.
It may be semi permanent, but you can devise a code of dots or slashes=20
if you want the marks to not be visible to the public.

For a short term study, you could easily notch the back of the shell=20
in different patterns with a little file --

Ron Brooks at the University of Guelph has been doing long-term =20
studies on painted turtles and marks them by painting a number on the =20
carapace.  I've done carapace notching myself and it's not that =20
difficult - you jst need to make sure not to go deeper than 1/3 of the =20
way into the scute.

I've also done volunteer work with a rehab centre that is rearing =20
endangered Wood Turtles.  They keep track of the individuals there by =20
marking the marginal scutes with nail polish since the carapaces are =20
too soft to notch when young - and they grow out quickly in younger =20
turtles.  THe nail polish doesn't last very long though, I believe it =20
has to be reapplied every month or so.

I meant to mention that one positive thing about painting something on =20
the backs of the turtles as Ron Brooks does, is that they can be =20
observed later without recapture.  Students could watch basking =20
turtles with binoculars to see if they are marked.

We mark limpets and snails in the rocky intertidal.  One low tech way to =
mark them is to use super glue and bee tags.  Another is to use =
differernt colors of permenant markers and then cover the marks with =
super glue.  Both should work on a turtle shell and should be pretty low =
cost.  The important thing is to make sure the shell is DRY when you =
mark them. Hope that helps.  I am sure if you're creative you can come =
up with some other non-intrusive ways to mark the shells.  The above =
methods last 

Position Announcement 2

[Michael Bykhovsky]

PhD position in Stream Ecology
Institute of Ecology, University of Georgia, Athens, GA

We are seeking a PhD student to join us in a large interdisciplinary project 
which has been recommended* for funding through the National Science 
Foundation’s (NSF) Frontiers in Biological Research (FIBR) Program: Linking 
genes to ecosystems: how do ecological and evolutionary processes interact in 
nature. The start date for this position is January 2007

The successful applicant will be based at the University of Georgia’s 
Institute of Ecology and will be part of an interdisciplinary research team 
composed of scientists from the University of Georgia, University of 
California, Riverside, Cornell University, the University of Nebraska, and 
several other universities.  Field research will be conducted in tropical 
streams of Trinidad and laboratory work at the University of Georgia’s 
Institute of Ecology.  The successful applicant will be involved in the 
characterization of tropical stream food webs using a variety of approaches 
(natural abundance stable isotopes; stoichiometry; experimental 15N additions). 
He/she will be involved in small-scale and whole-stream manipulative 
experiments.  He/she will have considerable intellectual freedom to develop 
independent research projects that compliment, but are distinct from goals of 
the main project.  Please contact Dr. Catherine Pringle at [EMAIL PROTECTED] if 
you would like furth!
 er information about this opportunity.

Please send a cover letter stating your accomplishments and interests, a 
curriculum vitae, any representative publications, and the names (and e-mail 
addresses of three references) by mail or email to: Dr. Catherine Pringle, 
Institute of Ecology, University of Georgia, Athens, GA ([EMAIL PROTECTED]) 

*Please Note: The Project has been recommended for funding - but is not yet 
funded - as of the posting of this advertisement (8/14/06). We anticipate 
hearing the final word in the next two weeks. 

Re: standard deviation of a slope

[Malcolm McCallum]

You can get teh Confidence interval and Prediction interval with most =
software.  I know MiniTab does it for regression, can't recall if SPSS =
does it, but probably does. =20
=20
VISIT HERPETOLOGICAL CONSERVATION AND BIOLOGY www.herpconbio.org =
=20
A New Journal Published in Partnership with Partners in Amphibian and =
Reptile Conservation
and the World Congress of Herpetology.
=20
Malcolm L. McCallum
Assistant Professor
Department of Biological Sciences
Texas A&M University Texarkana
2600 Robison Rd.
Texarkana, TX 75501
O: 1-903-223-3134
H: 1-903-791-3843
Homepage: https://www.eagle.tamut.edu/faculty/mmccallum/index.html
=20



From: Ecological Society of America: grants, jobs, news on behalf of =
Anon.
Sent: Wed 8/16/2006 8:39 AM
To: ECOLOG-L@LISTSERV.UMD.EDU
Subject: Re: standard deviation of a slope



Sarah Gilman wrote:
> Is it possible to calculate the standard deviation of the slope of a=20
> regression line and does anyone know how?  My best guess after=20
> reading several stats books is that the standard deviation and the=20
> standard error of the slope are different names for the same thing.
>
Technically, the standard error is the standard deviation of the
sampling distribution of a statistic, so it is the same as the standard
deviation.  So, you're right.

> The context of this question is  a manuscript comparing the=20
> usefulness of regression to estimate the slope of a relationship=20
> under different environmental conditions.  A reviewer suggested=20
> presenting the standard deviation of the slope rather than the=20
> standard error to compare the precision of the regression under=20
> different conditions.  For unrelated reasons, the sample sizes used=20
> in the compared regressions vary  from 10 to 200.  The reviewer=20
> argues that the sample size differences are influencing the standard=20
> error values, and so the standard deviation (which according to the=20
> reviewer doesn't incorporate the sample size) would be a more robust=20
> comparison of the precision of the slope estimate among these=20
> different regressions.
>
Well of course the sample sizes differences are influencing the standard
error values!  And so they should: if you have a larger sample size,
then the estimates are more accurate.  Why would one want anything other
than this to be the case?

In some cases, standard errors are calculated by dividing a standard
deviation by sqrt(n), but these are only special cases.

It may be that the reviewer can provide further enlightenment, but from
what you've written, I'm not convinced that they have the right idea.

Bob

--
Bob O'Hara

Dept. of Mathematics and Statistics
P.O. Box 68 (Gustaf H"llstr"min katu 2b)
FIN-00014 University of Helsinki
Finland

Telephone: +358-9-191 51479
Mobile: +358 50 599 0540
Fax:  +358-9-191 51400
WWW:  http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results - EEB: http://www.jnr-eeb.org

Re: standard deviation of a slope

[Geoffrey Poole]

Sarah:

I think the reviewer comment has merit.

I understand your problem as follows:  Your goal is to compare the 
"usefulness" (not sure what you means by "usefulness", but we'll go with 
it...) of a regressions across environmental conditions.  However, under 
one set of environmental conditions the regression might be based on 10 
points, but under another set of conditions, it might be based on 100 
points.

Unfortunately, even under the SAME environmental conditions, the SE of 
the slope will decrease as the sample size increases.  Thus, if the 
number of points varies across environmental conditions, you don't know 
if changes in the SE of the slope are caused by differences in sample 
size or differences in "usefulness" across conditions.

In section 17.3 "Testing the significance of a regression" of Zar's 
"Biostatistical Analysis" (pages 334-5 of forth edition) there is a clue 
that might help you with your dilemma...

Zar notes that the "standard error of estimate" (AKA "standard error of 
the regression") is a measure of the remaining variance in Y *after* 
taking into account the dependence of Y on X.  However, since the 
magnitude of this value is proportional to the magnitude of the 
dependent variable, Y, "examination of [this statistic is] a poor method 
for comparing regressions.  Thus, Dapson (1980) recommends using [the 
standard error of estimate divided by the mean of Y] (a unitless 
measure) to judge regression fits."

As I understand things (and I caution you that this could be wrong), the 
standard error of estimate (i.e., the variance of Y after taking into 
account the dependence of Y on X) should be independent of the number of 
points in the regression.  Therefore, is seems a good candidate for your 
comparisons.  An issue arises, however, if the mean of your Y values is 
different across environmental conditions.  In this case, you may have 
to normalize your "standard error of the estimate" by dividing by the 
mean of Y for each regression, as suggested by Dapson (1980) (as cited 
in Zar 1999).

Zar, J. H. 1999. Biostatistical analysis, fourth edition. Prentice Hall, 
Upper Saddle River, New Jersey.

Dapson, R. W. 1980.  Guidelines for statistical usage in age-estimation 
techniques. J. Wildlife Manage. 44:541-548 (as cited in Zar 1999)

I'm not sure this is the solution because I'm not a statistician and I 
haven't read Dapson's paper, but I'm pretty sure the reviewer has a 
legitimate point about your comparisons (as I described above) and I 
hope these references will help you find your answer.

I'm posting this to the general list serve in hopes that others out 
there will correct, improve upon, or confirm my thoughts.

-Geoff Poole



Anon. wrote:
> Sarah Gilman wrote:
> 
>> Is it possible to calculate the standard deviation of the slope of a  
>> regression line and does anyone know how?  My best guess after  
>> reading several stats books is that the standard deviation and the  
>> standard error of the slope are different names for the same thing.
>>
> Technically, the standard error is the standard deviation of the 
> sampling distribution of a statistic, so it is the same as the standard 
> deviation.  So, you're right.
> 
>> The context of this question is  a manuscript comparing the  
>> usefulness of regression to estimate the slope of a relationship  
>> under different environmental conditions.  A reviewer suggested  
>> presenting the standard deviation of the slope rather than the  
>> standard error to compare the precision of the regression under  
>> different conditions.  For unrelated reasons, the sample sizes used  
>> in the compared regressions vary  from 10 to 200.  The reviewer  
>> argues that the sample size differences are influencing the standard  
>> error values, and so the standard deviation (which according to the  
>> reviewer doesn't incorporate the sample size) would be a more robust  
>> comparison of the precision of the slope estimate among these  
>> different regressions.
>>
> Well of course the sample sizes differences are influencing the standard 
> error values!  And so they should: if you have a larger sample size, 
> then the estimates are more accurate.  Why would one want anything other 
> than this to be the case?
> 
> In some cases, standard errors are calculated by dividing a standard 
> deviation by sqrt(n), but these are only special cases.
> 
> It may be that the reviewer can provide further enlightenment, but from 
> what you've written, I'm not convinced that they have the right idea.
> 
> Bob
> 

Re: standard deviation of a slope

[Stephen B. Cox]

Sarah - a "standard error" is the standard deviation of a statistic within a
sampling distribution.  Most of the time we talk about the standard error of
the mean - but other statistics (i.e., parameter etimates), like a
regression slope, also have standard errors.  So, yes, the se is the sd of
the slope in that sense.  However, slope estimates repeatedly derived from
large samples will tend to be more consistent than slope estimates from
small samples.  Hence, sample size does influence the se of slope.  In fact,
this is one reason it is used as a measure of the precision of the slope
estimate.  Without any other details, I am unsure why you would not want to
consider sample size in your estimate of "precision."

Stephen

On 8/15/06, Sarah Gilman <[EMAIL PROTECTED] > wrote:
>
> Is it possible to calculate the standard deviation of the slope of a
> regression line and does anyone know how?  My best guess after
> reading several stats books is that the standard deviation and the
> standard error of the slope are different names for the same thing.
>
> The context of this question is  a manuscript comparing the
> usefulness of regression to estimate the slope of a relationship
> under different environmental conditions.  A reviewer suggested
> presenting the standard deviation of the slope rather than the
> standard error to compare the precision of the regression under
> different conditions.  For unrelated reasons, the sample sizes used
> in the compared regressions vary  from 10 to 200.  The reviewer
> argues that the sample size differences are influencing the standard
> error values, and so the standard deviation (which according to the
> reviewer doesn't incorporate the sample size) would be a more robust
> comparison of the precision of the slope estimate among these
> different regressions.
>
> The textbooks I've read suggest that the se of the slope is actually
> the sd, and doesn't include an extra division by the sample size as
> the se of a population mean would.
>
> Any enlightment would be greatly appreciated.
>
> - Sarah
> -
> Sarah Gilman, PhD
>
> Friday Harbor Laboratories
> University of Washington
> 620 University Rd.
> Friday Harbor, WA 98250
>
> 360-378-2165
>  [EMAIL PROTECTED]
> http://faculty.washington.edu/gilmans
> -
>

Why not a law..Evolution

[Malcolm McCallum]

I wonder if it is time to stop calling it the "Theory of Evolution" and =
start calling it the "Law of Evolution,"  and to stop referring to =
"evolutionary theory" and surplant that with "evolutionary law."=20
=20
Lets face it, there has to be more evidence for evolution than there was =
for Gravity, etc. when they were moved to law status.
=20
Do we know of any case where organisms were not adapted by or succumb to =
some outside force? =20
=20
Sounds like a law to me. =20
=20
VISIT HERPETOLOGICAL CONSERVATION AND BIOLOGY www.herpconbio.org =
=20
A New Journal Published in Partnership with Partners in Amphibian and =
Reptile Conservation
and the World Congress of Herpetology.
=20
Malcolm L. McCallum
Assistant Professor
Department of Biological Sciences
Texas A&M University Texarkana
2600 Robison Rd.
Texarkana, TX 75501
O: 1-903-223-3134
H: 1-903-791-3843
Homepage: https://www.eagle.tamut.edu/faculty/mmccallum/index.html
=20



From: Ecological Society of America: grants, jobs, news on behalf of =
Ashwani Vasishth
Sent: Tue 8/15/2006 10:13 PM
To: ECOLOG-L@LISTSERV.UMD.EDU
Subject: Commentaries on science and on evolution



There are two commentaries in the current issue of Bioscience that I =
thought worth considering, in the particular context of the current =
"debate" about the teaching of evolution science in our schools

The first, by Ross H. Nehm, "Faith-based Evolution Education?" (638 =
BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org) argues =
that scientists, generally defined, have limited themselves to =
generating belief statements on evolution, rather than scientifically =
and systematically addressing the misconceptions inherent in lay beliefs =
and in creationist rhetoric.  In addition, we need to get much better at =
showing people why a knowledge of evolution science matters, to everyday =
folks, on an everyday basis.

The second, by Margaret Wertheim, "Who Is Science Writing For?" (640 =
BioScience * August 2006 / Vol. 56 No. 8 www.biosciencemag.org), argues =
that science writers, generally defined, are not positioning themselves =
where the readers are, in America, but rather are catering to a very =
narrow (and quite small) self-selecting cluster of individuals who =
actively seek out science-related material.  We need to get better at =
doing what she calls "missionary work."

Cheers,
-
  Ashwani
 Vasishth  [EMAIL PROTECTED]  (818) 677-6137
 Department of Urban Studies and Planning, ST 206
California State University, Northridge
 http://www.csun.edu/~vasishth/

Re: standard deviation of a slope

[David Bryant]

Bob,

I have a similar question to Sarah's and it may even be the same;   
I'm using orthogonal regression to determine the equivalence of two  
variables, both with errors.  I want to use the S.E. of the slope to  
compare to the optimum slope of one (equivalence among variable  
responses).  I contacted JMP (SAS institute) and they recommend the  
two-one-sided test (TOST)  which I understand as simply increasing  
the alpha to 0.10.  But this still gives a very large confidence  
interval providing a less than robust test.  In some instances a  
slope of 2 is not significantly different than slope of 1.  (!!??) In  
fact I have not found one instance in which the slopes differ.  This  
seems like a universal type II error to me.

Can I use the standard test of homogeneity of slopes used in ANCOVA  
and compare to 1  (s.e. =0)  or would that lead to a type I error?

Thanks for your time,

David

David M Bryant Ph D
University of New Hampshire
Environmental Education Program
Durham, NH 03824

[EMAIL PROTECTED]
978-356-1928



On Aug 16, 2006, at 9:39 AM, Anon. wrote:

> Sarah Gilman wrote:
>> Is it possible to calculate the standard deviation of the slope of a
>> regression line and does anyone know how?  My best guess after
>> reading several stats books is that the standard deviation and the
>> standard error of the slope are different names for the same thing.
>>
> Technically, the standard error is the standard deviation of the
> sampling distribution of a statistic, so it is the same as the  
> standard
> deviation.  So, you're right.
>
>> The context of this question is  a manuscript comparing the
>> usefulness of regression to estimate the slope of a relationship
>> under different environmental conditions.  A reviewer suggested
>> presenting the standard deviation of the slope rather than the
>> standard error to compare the precision of the regression under
>> different conditions.  For unrelated reasons, the sample sizes used
>> in the compared regressions vary  from 10 to 200.  The reviewer
>> argues that the sample size differences are influencing the standard
>> error values, and so the standard deviation (which according to the
>> reviewer doesn't incorporate the sample size) would be a more robust
>> comparison of the precision of the slope estimate among these
>> different regressions.
>>
> Well of course the sample sizes differences are influencing the  
> standard
> error values!  And so they should: if you have a larger sample size,
> then the estimates are more accurate.  Why would one want anything  
> other
> than this to be the case?
>
> In some cases, standard errors are calculated by dividing a standard
> deviation by sqrt(n), but these are only special cases.
>
> It may be that the reviewer can provide further enlightenment, but  
> from
> what you've written, I'm not convinced that they have the right idea.
>
> Bob
>
> -- 
> Bob O'Hara
>
> Dept. of Mathematics and Statistics
> P.O. Box 68 (Gustaf H„llstr”min katu 2b)
> FIN-00014 University of Helsinki
> Finland
>
> Telephone: +358-9-191 51479
> Mobile: +358 50 599 0540
> Fax:  +358-9-191 51400
> WWW:  http://www.RNI.Helsinki.FI/~boh/
> Journal of Negative Results - EEB: http://www.jnr-eeb.org

EPA Job Opportunity ecology concentration

[Nadine Lymn]

The Environmental Protection Agency, Office of Atmospheric Programs,
Washington DC

Environmental Protection Specialist - ecology concentration (Ph.D)
Potential Salary Range: GS - 11/13

The Assessment and Communications Branch in the Clean Air Markets
Division (CAMD) has an exciting and challenging opportunity to work in
the Washington, DC area assessing environmental changes as a result of
air quality regulations.  CAMD has the responsibility of implementing
and assessing several national and regional market-based emission
reduction programs for power plants, including the Acid Rain Program,
the NOx Budget Trading Program, the Clean Air Interstate Rule, and the
Clean Air Mercury Rule.  CAMD has the need for an individual with
education and training in ecology or environmental science to assess the
ecological and environmental changes that result from implementation of
these air pollution control programs.  

The incumbent will be responsible for working in partnership with other
EPA offices, other federal agencies, and scientists outside government
to assess ecological and environmental changes in a variety of
ecosystems, including estuaries, lakes and streams, and forests. These
changes will be measured as both chemical changes (e.g. acid-base status
of lakes or forest soils) and biological changes (e.g. communities of
phytoplankton or fish). The position includes interpretation of
atmospheric and ecological monitoring and modeling results for
scientific and non-scientific audiences. The incumbent will keep
up-to-date on the relevant scientific literature, including monitoring
programs and available models; contribute to office- and agency-wide
reports and publications; develop and manage ecological assessment
projects with contractors, grantees, and other EPA staff; interact with
senior agency staff; and communicate information about basic ecological
science and analytical results to scientific and non-scientific
audiences both inside and outside EPA. 

Interested candidates should be enthusiastic, organized self-starters
with a Ph.D in ecology, environmental science, or a related field, with
experience in assessing environmental change as a result of policy
implementation.  Candidates should have knowledge and education
regarding biogeochemical cycles of major elements (e.g. sulfur,
nitrogen, and mercury) and their ecological impacts. Experience
assessing ecological response to changes in atmospheric concentration
and deposition of sulfur compounds, nitrogen compounds, and/or mercury
is strongly preferred. The candidate must also demonstrate the
analytical capability to understand scientific data, writing skills, and
the capacity to convert complex information into easy-to-understand
information for non-scientific audiences.   

EPA offers a competitive total rewards program with opportunities for
growth and development.   EPA is an Equal Opportunity Employer.
Selection for this position will be based solely on merit without regard
to race, color, religion, age, gender, national origin, political
affiliation, disability, sexual orientation, marital or family status or
any other non-merit factors. Applicant must be a U.S. Citizen.

This is not an official job application process, but a solicitation for
resumes.  The job will be announced through EPA's EZ hire employment
system in the next few months.

Please e-mail your resume to Tamara Saltman at [EMAIL PROTECTED] or
Richard Haeuber at [EMAIL PROTECTED] if you are interested in this
position.

Re: standard deviation of a slope

[Anon.]

Sarah Gilman wrote:
> Is it possible to calculate the standard deviation of the slope of a  
> regression line and does anyone know how?  My best guess after  
> reading several stats books is that the standard deviation and the  
> standard error of the slope are different names for the same thing.
> 
Technically, the standard error is the standard deviation of the 
sampling distribution of a statistic, so it is the same as the standard 
deviation.  So, you're right.

> The context of this question is  a manuscript comparing the  
> usefulness of regression to estimate the slope of a relationship  
> under different environmental conditions.  A reviewer suggested  
> presenting the standard deviation of the slope rather than the  
> standard error to compare the precision of the regression under  
> different conditions.  For unrelated reasons, the sample sizes used  
> in the compared regressions vary  from 10 to 200.  The reviewer  
> argues that the sample size differences are influencing the standard  
> error values, and so the standard deviation (which according to the  
> reviewer doesn't incorporate the sample size) would be a more robust  
> comparison of the precision of the slope estimate among these  
> different regressions.
> 
Well of course the sample sizes differences are influencing the standard 
error values!  And so they should: if you have a larger sample size, 
then the estimates are more accurate.  Why would one want anything other 
than this to be the case?

In some cases, standard errors are calculated by dividing a standard 
deviation by sqrt(n), but these are only special cases.

It may be that the reviewer can provide further enlightenment, but from 
what you've written, I'm not convinced that they have the right idea.

Bob

-- 
Bob O'Hara

Dept. of Mathematics and Statistics
P.O. Box 68 (Gustaf H„llstr”min katu 2b)
FIN-00014 University of Helsinki
Finland

Telephone: +358-9-191 51479
Mobile: +358 50 599 0540
Fax:  +358-9-191 51400
WWW:  http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results - EEB: http://www.jnr-eeb.org

EPA Job Opportunity ecology concentration, mercury focus

[Nadine Lymn]

The Environmental Protection Agency, Office of Atmospheric Programs,
Washington DC

Environmental Protection Specialist - Ecology Concentration, Mercury
focus (M.S./M.A.)
Potential Salary Range: GS - 9

The Assessment and Communications Branch in the Clean Air Markets
Division (CAMD) has an exciting and challenging opportunity to work in
the Washington, DC area assessing environmental changes as a result of
air quality regulations.  CAMD has the responsibility of implementing
and assessing several national and regional market-based emission
reduction programs for power plants, including the Acid Rain Program,
the NOx Budget Trading Program, the Clean Air Interstate Rule, and the
Clean Air Mercury Rule.  CAMD has the need for an individual with
education and training in ecology or environmental science to assess the
ecological and environmental changes that result from implementation of
these air pollution control programs.  

The incumbent will be responsible for working in partnership with other
EPA offices, other federal agencies, and scientists outside government
to assess ecological and environmental changes in a variety of
ecosystems, including estuaries, lakes and streams, and forests, as a
result of changes in emissions from power plants. These changes will be
measured as both chemical changes (e.g. acid-base status of lakes or
forest soils) and biological changes (e.g. communities of phytoplankton
or fish). The position includes interpretation of atmospheric and
ecological monitoring and modeling results for scientific and
non-scientific audiences. The incumbent will keep up-to-date on the
relevant scientific literature, including monitoring programs and
available models; contribute to office- and agency-wide reports and
publications; develop and manage ecological assessment projects with
contractors, grantees, and other EPA staff; interact with senior agency
staff; and communicate information about basic ecological science and
analytical results to scientific and non-scientific audiences both
inside and outside EPA. 

Interested candidates should be enthusiastic, organized self-starters
with an advanced degree (M.A., M.S.) in ecology, environmental science,
biology, or a related field, including knowledge and education regarding
biogeochemical cycles of major elements (e.g. sulfur, nitrogen, and
mercury), and their ecological impacts. Candidates should have
experience or interest in assessing environmental changes as a result of
policy implementation.  Experience assessing ecological response to
changes in atmospheric concentration and deposition of sulfur compounds,
nitrogen compounds, and/or mercury is strongly preferred. The candidate
must also demonstrate the analytical capability to understand scientific
data, writing skills, and the capacity to convert complex information
into easy-to-understand information for non-scientific audiences.   

EPA offers a competitive total rewards program with opportunities for
growth and development.   EPA is an Equal Opportunity Employer.
Selection for this position will be based solely on merit without regard
to race, color, religion, age, gender, national origin, political
affiliation, disability, sexual orientation, marital or family status or
any other non-merit factors. Applicant must be a U.S. Citizen.

This is not an official job application process, but a solicitation for
resumes.  The job will be announced through EPA's EZ hire employment
system in the next few months.

Please e-mail your resume to Tamara Saltman at [EMAIL PROTECTED] or
Richard Haeuber at [EMAIL PROTECTED] if you are interested in this
position.

Underwater epoxy for attaching markers

[lisa jones]

Hi,

I am attempting to set up an underwater experiment (freshwater) where I will 
need to mark off quadrats that I have cleared on a concrete wall. I am 
planning on attaching plastic/metal markers to each corner of the quadrat - 
each marker will be about 2cm in diameter and weigh ~2-3 grams.

I need to use an underwater epoxy to attach these markers and was wondering 
if anyone knows of a good underwater epoxy that could be easily used with 
SCUBA diving and if you know of any place to get an epoxy that comes with an 
underwater applicator as well.

Please contact me either at this email address or at 
[EMAIL PROTECTED] if you have any information that could help me.

Cheers,

Lisa Jones
PhD Candidate
Redpath Museum
McGill University

_
Play Q6 for your chance to WIN great prizes.  
http://q6trivia.imagine-live.com/enca/landing

standard deviation of a slope

[Sarah Gilman]

Is it possible to calculate the standard deviation of the slope of a  
regression line and does anyone know how?  My best guess after  
reading several stats books is that the standard deviation and the  
standard error of the slope are different names for the same thing.

The context of this question is  a manuscript comparing the  
usefulness of regression to estimate the slope of a relationship  
under different environmental conditions.  A reviewer suggested  
presenting the standard deviation of the slope rather than the  
standard error to compare the precision of the regression under  
different conditions.  For unrelated reasons, the sample sizes used  
in the compared regressions vary  from 10 to 200.  The reviewer  
argues that the sample size differences are influencing the standard  
error values, and so the standard deviation (which according to the  
reviewer doesn't incorporate the sample size) would be a more robust  
comparison of the precision of the slope estimate among these  
different regressions.

The textbooks I've read suggest that the se of the slope is actually  
the sd, and doesn't include an extra division by the sample size as  
the se of a population mean would.

Any enlightment would be greatly appreciated.

- Sarah
-
Sarah Gilman, PhD

Friday Harbor Laboratories
University of Washington
620 University Rd.
Friday Harbor, WA 98250

360-378-2165
[EMAIL PROTECTED]
http://faculty.washington.edu/gilmans
-

Commentaries on science and on evolution

[Ashwani Vasishth]

There are two commentaries in the current issue of Bioscience that I thought 
worth considering, in the particular context of the current "debate" about the 
teaching of evolution science in our schools

The first, by Ross H. Nehm, "Faith-based Evolution Education?" (638 BioScience 
* August 2006 / Vol. 56 No. 8 www.biosciencemag.org) argues that scientists, 
generally defined, have limited themselves to generating belief statements on 
evolution, rather than scientifically and systematically addressing the 
misconceptions inherent in lay beliefs and in creationist rhetoric.  In 
addition, we need to get much better at showing people why a knowledge of 
evolution science matters, to everyday folks, on an everyday basis.

The second, by Margaret Wertheim, "Who Is Science Writing For?" (640 BioScience 
* August 2006 / Vol. 56 No. 8 www.biosciencemag.org), argues that science 
writers, generally defined, are not positioning themselves where the readers 
are, in America, but rather are catering to a very narrow (and quite small) 
self-selecting cluster of individuals who actively seek out science-related 
material.  We need to get better at doing what she calls "missionary work."

Cheers,
-
  Ashwani
 Vasishth  [EMAIL PROTECTED]  (818) 677-6137
 Department of Urban Studies and Planning, ST 206
California State University, Northridge
 http://www.csun.edu/~vasishth/