 |
Graeme Ambler's HomepageHi, welcome to my home page! Until recently, I was a research assistant in the Statistics group (part of the Department of Mathematics) at the University of Bristol. The project I was working on is to do with Bayesian analysis of gene expression data. I'm now pursuing a career change so am writing up my work and tying up loose ends. |
Research
Papers
Ambler, G. K. and Silverman, B. W. (2004) Perfect simulation for Bayesian wavelet thresholding with correlated coefficients. Submitted to the Journal of the Royal Statistical Society, Series B. pdf of paper software
Ambler, G. K. and Silverman, B. W. (2004) Perfect simulation of spatial point processes using dominated coupling from the past with application to a multiscale area-interaction point process. Submitted to the Journal of Applied Probability. pdf of paper software
Hein, A.-M.K., Richardson, S., Causton, H.C., Ambler, G.K., Green, P.J. (2004). BGX: a fully Bayesian gene expression index for Affymetrix GeneChip data. Submitted to Biostatistics. pdf of paper software and supplementary material
Burke, A., Eisenmann, V., Ambler, G. K. (2003) The systematic position of Equus hydruntinus, an extinct species of Pleistocene equid. Quaternary Research 59, 459-469. abstract
Technical reports
Ambler, G. K. and Silverman, B. W. (2004) Perfect simulation for wavelet thresholding with correlated coefficients. Technical Report 04:01, Department of Mathematics, University of Bristol. (PDF)
Ambler, G. K. (2003) A generic MCMC implementation in C++ based around specification of the model DAG. Technical Report 03:09, Department of Mathematics, University of Bristol. (PDF)
Thesis
Ambler, G. K. (2002) Dominated Coupling From The Past and Some Extensions of the Area-Interaction Process. (PDF, Bzip2'd postscript).
I wrote some programs to simulate some of the models in my thesis. They are available here: phdcode.tar.bz2.
If anyone doesn't know what bzip2 is, have a look here: Bzip2.
Other
I won second prize in the poster competition poster at the 2003 Royal Statistical Society annual conference. It's rather large (4MB), so don't download this over a slow link!
Ambler, G. K. (2003) Bayesian two-way clustering for gene expression data. (PDF)
Here's a copy of my CV.
Teaching
Last year I lectured Statistics For Scientists. I have no teaching responsibilities this year.
Useful Links
An annotated bibliography of Perfect Simulation (a major component of my thesis).
The Royal Statistical Society Avon local group web page.
The Bayesian Cake Club web site.
Contact Details
The best way to contact me is via email. My address is
Graeme<at>Ambler<dot>me<dot>uk.Sorry about the rather obscure form of the address, I'm fed up getting so much spam. I can also be contacted via snail mail:
School of MathematicsUniversity of Bristol
University Walk
Bristol
U.K.
BS8 1TW
| Page maintained by Graeme Ambler. Last modified on Saturday the 24th of July 2004. |