Re: About the Bootstrap...

Gilles Escarguel wrote:

> Dear all,
>
> I have two simple questions about the bootstrap technique to estimate
> confidence levels on edges and nodes.
>
> First, it seems to me that authors have different definitions on what is
> a *parametric* bootstrap. Is it: (i) a resampling procedure allowing to
> assess confidence levels on an a priori phylogenetic hypothesis -- a
> parametric topology -- given the available data, or (ii) a resampling
> procedure without any a priori hypothesis but recquiring confidence
> intervals (e.g., standard errors) linked to each descriptor (mean
> values) for each analyzed taxon to be known in order to generate
> pseudo-samples (e.g., by gaussian random drawing from N[mean; S.E.])? In
> this second case, parametric bootstrap cannot be used with molecular
> data and discrete morphological data (0/1), but can easilly be used with
> biometrical and/or morphometrical data in association with distance
> methods. If (ii) is not what is usually named a parametric bootstrap,
> what it is? Is it known if confidence levels estimated with this second
> resampling procedure have the same properties than more classic
> nonparametric (1st order) bootstrap CL?


iii. A parametric bootstrap generates its pseudoreplicate data sets 
using an explicit model of evolution abstracted from the data, rather 
than resampling the actual data as in a non-parametric bootstrap. If, 
for example, I wanted to get bootstrapped data sets for a set of DNA 
sequences, I might first estimate a tree using some phylogenetic 
analysis program, then estimate evolutionary parameters over that tree 
(transition/transversion ratio, proportion of invariable sites, base 
composition, etc.), and then plug those parameters and that tree into an 
evolution simulation program to get a new data set. Repeated many times, 
I would have a set of pseudoreplicate data sets. Those pseudoreplicates 
can then be used for all sorts of purposes. See this for example:

Huelsenbeck, J. P., D. M. Hillis, and R. Jones. 1996. Parametric 
bootstrapping in molecular phylogenetics: Applications and performance. 
Pages 19-45 in  Molecular zoology: Advances, strategies, and protocols 
(J. D. Ferraris and S. R. Palumbi, eds.). Wiley.

> Second, since Efron's et al. (1996: PNAS, 93: 7085-7090) paper on second
> order bootstrap confidence levels computation, does anyone here know if
> algorithms and/or programs allowing to compute them in association with
> distance methods (e.g., L.S. or N.J.)  have been published? I think the
> last version of Phylip (3.6alpha3) does not allow to compute them -- it
> should be an interesting improvment of this package!


I know nothing about this.