[quick links] Scientific misconduct and scientific inability

• Janet D. Stemwedel has three interesting posts about scientific misconduct
• Comments by David Smith and Andrew Gelman, with follow-ups, about the misuse of statistical tests.

Recent CUDA applications

Taking a look at Nvidia's CUDA zone I found some recent additions - besides important ones that I already knew like the Smith-Waterman and the phylogenetic likelihood algoritihms. Here is a list of these new programs and libraries that take advantage of GPUs:

1. Expectation Maximization algorithm for Gaussian Mixture Models
2. Multilevel algorithm for MDS (multidimensional scaling)
3. Multiclass classifier based on SVMs (support vector machines)
4. GPU computing in the R statistical environment (BLAS lowlevel routines and dist(), hclust(), cor(), and granger.test() functions)
5. Smith-Waterman algorithm for sequence database search
6. Quicksort library
7. Feature finding algorithm for mass spectrometry
8. Smith-Waterman algorithm for sequence alignment
9. MDR (multifactor dimensionality reduction) algorithm for detecting genetic epistatic interactions (white paper)
   

The last reference is just a two-page summary, and the 8th reference is behind a paywall - I couldn't access it myself - but the slides are available here.

Powered by ScribeFire.

Phylogenetics, by Joe Felsenstein

Luke J. Harmon and Dan Rabosky recently e-enterviewed Joe Felsenstein. Here are some interesting points:

Luke: What are the most exciting recent developments in systematics / comparative methods?

Joe: The availability of genome-scale information is certainly one. The arrival of a generation of young researchers who are comfortable with statistical and computational approaches is another. But the most important development is reflected in recent work on coalescent trees of gene copies within trees of species. What this does is tie together between-species molecular evolution and within-species population genetics. Those two lines of work have been developing almost independently since the 1960s. But now, with population samples of sequences at multiple loci in multiple related species, they are coming back together. This is not another Modern Synthesis, but it is a major event that needs a name. How about the "Family Reunion"? Long-estranged relatives who have not been in touch are getting together.

(...)

Luke: What do you think about the current trend in phylogenetics (and, lately, comparative biology) towards Bayesian approaches?

Joe: I am a curmudgeon on this, in that Bayesian approaches do not feel right to me. So I have been resisting them. Bayesians were unhappy with the treatment of Bayesian Inference in my book, in that I did not give them four chapters, the last of which ended by declaring victory. I think we're all Bayesians when we come to cross the street, balancing evidence of approaching cars against our priors. But that's where one of the criticisms of Bayesianism comes in -- do we all have the same priors? Is there necessarily a single prior that you can use that will be broadly acceptable to your readership? If not, then maybe the reader of the paper should instead be given the likelihood curve so they can apply their own prior to it. For phylogenies, priors giving equal probability to all topologies (or to all labeled histories) would be noncontroversial. But the part of the prior that puts distributions on branch lengths could be wildly controversial. There is also the issue of whether some things, such as whether the sun will rise tomorrow morning, really should have a prior.

People should be Bayesians if that fits with their philosophy of doing science. But not just because a Bayesian program happens to run faster than a non-Bayesian one. They should also realize that we will continue to have both Bayesians and non-Bayesians. Biologists sometimes think that this controversy emerged in their field and will be settled there -- that one more really good argument and everyone will become a Bayesian. They might not be aware that Bayesian arguments have been around since 1764. There is no new decisive argument that's going to arise in our field.

The issue to contemplate is the priors, not the details of MCMC techniques. We have not yet seen a case where an important conclusion depends strongly on what prior you assume. Perhaps we never will, but if a case like that arises, and causes trouble for Bayesian approaches, people should not be too surprised.

The commentaries are also very enlightening.

Powered by ScribeFire.