Hello all,
For advice on the use of the arcsin transform, I
recommend the following paper:

http://www.esajournals.org/doi/abs/10.1890/10-0340.1

The title itself is worth poking the link.

David Schneider


Quoting Jordan Marshall <[email protected]>:

> Brian
> 
> I use arcsin(square root(proportion)) anytime I'm doing analysis of
> percent data. The reason may not be justified for the type of simulation
> your running, which I'm not familiar with. I use this transformation
> since percent data is inherently not normally distributed.
> Arcsin(sqrt(proportion)) does transform the data to near normal
> distribution.
> 
> Jordan
> 
> -- 
> Jordan M. Marshall, PhD
> Assistant Professor
> Department of Biology
> Indiana University-Purdue University Fort Wayne
> 2101 E. Coliseum Blvd.
> Fort Wayne, IN 46805
> 
> Office (260) 481-6038
> Mobile (865) 919-9811
> Fax    (260) 481-6087
> 
> www.jordanmarshall.com 
> 
> >>> On 11/30/2011 at 12:00 AM, ECOLOG-L automatic digest system
> <[email protected]> wrote:
> > Date:    Tue, 29 Nov 2011 14:33:19 -0500
> > From:    =?ISO-8859-1?Q?Brian_Mitchell?= <[email protected]>
> > Subject: Transformation of percent cover data for power analysis
> > 
> > Hello ecolog,
> > 
> > I am working on a power analysis simulation for long-term forest
> monitoring
> > data, with the goal of documenting our power to detect trends over
> time. 
> > The simulation is based on a repeated measures hierarchical model,
> where
> > future data is simulated based on the initial data set and a
> bootstrap of
> > pilot data differences between observation periods, multiplied by a
> range of
> > effect sizes (50% decline to 50% increase).
> > 
> > My question is about the appropriate transformation to use for
> percent cover
> > data in this simulation. I don’t want to use raw percentages
> because the
> > simulation will easily result in proportions less than zero or
> greater than
> > one.  Similarly, a log transform can easily result in
> back-transformed
> > proportions greater than one.  Most other transforms I’ve looked at
> would
> > not prevent back-transformed data from exceeding one or the other
> > boundaries.  The exception is the logistic transform, which would
> indeed
> > force all simulated data to be between zero and one when
> back-transformed. 
> > However, the logistic transform gives values of negative infinity for
> a
> > percent cover of zero, and positive infinity for a percent cover of
> one.  I
> > was thinking that adding a tiny number to zeros and subtracting a
> tiny
> > number from ones (e.g., 0.00001) would solve the problem (roughly
> equivalent
> > to a log of x+1 transform), but I have been unable to find reference
> to
> > anyone using this approach for percent cover data.  Does anyone have
> any
> > thoughts about the validity of my proposed approach or of another
> approach
> > that would help solve my problem?
> > 
> > Thanks!
> > 
> > Brian Mitchell
> > NPS Northeast Temperate Network Program Manager
> > Adjunct Assistant Professor, University of Vermont
> > [email protected]  
> 




This electronic communication is governed by the terms and conditions at
http://www.mun.ca/cc/policies/electronic_communications_disclaimer_2011.php

Reply via email to