Dear William.
The sigma^2 parameter in a fitted Brownian model is a rate in the sense
that it is the rate at which variation (variance) would be expected to
accumulate per unit of time among a set of lineages that were evolving
according to a random diffusion (Brownian) process. If you think
I am using fitContinuous to model karyotype evolution and trying to understand
the meaning of the sigma-squared parameter in the output by drawing very simple
trees and phenotype vectors. However, the output sigma-squared values do not
obviously correspond to any obvious variance calculation.
Dear Carl, Liam, and others,
thanks for your explanation of what went wrong in the fitContinuous
calculations. I set beta to a large number (100) in order to
stop it from reading the maximum value. Then, I got exactly the same
results for lambda with the non-multiplied and the
Hi Annemarie,
No problem, tried to give some answers below.
On Mon, May 23, 2011 at 8:05 AM, Annemarie Verkerk annemarie.verk...@mpi.nl
wrote:
Dear Carl, Liam, and others,
thanks for your explanation of what went wrong in the fitContinuous
calculations. I set beta to a large number
Hi Annemarie,
The only thing I would add to Carl's comment is that the theoretical
limit of lambda is not 1.0, but can be found (for an ultrametric tree)
by computing:
C-vcv.phylo(tree)
maxLambda-max(C)/max(C[upper.tri(C)])
You can then change the boundary condition for fitContinuous():
Hi Carl, Annemarie-
While it is possible in principle that Annemarie's results reflect true ML
estimate of lambda = 1, I think the practical reason this is occurring is that
the default bounds on lambda in fitContinuous are 1e-7 and 1. Because
optimization in fitContinuous uses a bounded BFGS
Hi,
As a followup on the questions regarding estimates of phylogenetic signal, I
was wondering if beta values could be meaningfully compared, for example if
estimated for different traits on the same phylogeny. Would it be correct to
assume that, if a Brownian motion model of evolution
Hi Annemarie,
Positive log-likelihoods are not a problem. The log-likelihood is
calculated by summing the log probability densities, which come from a
function that integrates to 1.0. Thus, if the variance of this
distribution is small, the value of the function will be large (i.e.,
Hi all,
It seems to be a popular week for questions!
I am running fitContinuous on a variety of continuous trait
data. I am noticing that when the traits are in units where
the max is less than 1 (these are not ratio data, though),
many of the various models produce log-likelihoods that are
Doh! Really should have remembered that,
likelihoods-can-be-greater-than-1 is likelihood 101...
I am still a little puzzled by the dramatically different
results between rescaling and not, will try to post an
example in a sec...
On 3/7/11 12:37 PM, Nick Matzke wrote:
Hi all,
It seems
Hi Nick-
Are you are getting differences in relative AICs between models from simple
rescaling (multiplying by a constant)?
The actual values of the traits *might* matter for optimization, depending on
various parameters associated with optimization (and whatever algorithm is
being used -
Ah, so while re-creating my problem for copy-paste-debug
goodness on the listserv, I discovered what was confusing me.
Originally, when I ran the various models, I got these
log-likelihoods for results:
==
tf2ic2kzkr
12 matches
Mail list logo