[R] Force regression line to a 1:1 relationship
gunter.berton at gene.com
Thu Sep 15 15:33:35 CEST 2011
This sounds like you need a mixed effects model (e.g. lme or lmer
instead of lm) instead of the possibly spurious adhocery that you
describe. I suggest you post your message on the SIG-mixed-effects
list and/or get help from a local statistician
On Thu, Sep 15, 2011 at 1:49 AM, RCulloch <ross.culloch at dur.ac.uk> wrote:
> Many thanks to all of you! AV plots are what I am trying to plot. Perhaps to
> reduce confusion I can give you an example of what I am doing:
> I am looking at behaviour of re-sighted individuals over two time points. I
> use lm() on these data and obtain the residuals.
> Then I am interested to know whether an individuals' residual is related to
> a site fidelity mesure over the two time periods. Such that an individual
> that maintains a high degree of site fidelity shows less variation (has a
> smaller residual value) in (for example) aggressive behaviour. Therefore,
> using the absolute values of the residuals (as I am not interested in less
> or more aggressive) I plot these against the site fidelity measure to assess
> whether there is a correlation.
> The 1:1 relationship was to assess the deviation from 'absolute agreement',
> where the method above takes into consideration plasticity/noise between the
> two time periods.
> I hope this is a little clear and, although not a quote from the reviewer,
> this is essentially what was suggested.
> View this message in context: http://r.789695.n4.nabble.com/Force-regression-line-to-a-1-1-relationship-tp3809733p3815014.html
> Sent from the R help mailing list archive at Nabble.com.
> R-help at r-project.org mailing list
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
"Men by nature long to get on to the ultimate truths, and will often
be impatient with elementary studies or fight shy of them. If it were
possible to reach the ultimate truths without the elementary studies
usually prefixed to them, these would not be preparatory studies but
-- Maimonides (1135-1204)
Genentech Nonclinical Biostatistics
More information about the R-help