The Wishart distribution and especially the inverse-Wishart distribution are the source of some confusion because they occasionally appear with alternative parameterizations. Also, the Wishart distribution can be used to model a covariance matrix or a precision matrix (the inverse of a covariance matrix) in different situations, and the inverse-Wishart the same, but the other way round. It’s already becoming complicated. Hal Stern, coauthor of Bayesian Data Analysis (BDA), helped to clarify many issues for me in an email conversation. In this post I hope to clarify the differences in Wishart parameterizations of BDA, the wikipedia pages, and WinBUGS and OpenBUGS softwares, and show an example in OpenBUGS where the inverse parameterization has to be specified relative to the distribution’s definition for the correct posterior to result.
Read more…
Erik Erhardt Statistics
Seymour Grufferman, Frederick Ruymann, Simona Ognjanovic, Erik B. Erhardt, and Harold M. Maurer.
Prenatal X-ray Exposure and Rhabdomyosarcoma in Children: A Report from the Children’s Oncology Group. Cancer Epidemiology Biomarkers & Prevention. April 2009, 18(4), OF1–6. [pdf]
This is the first in a series of papers that will be the result of my research assistantship Fall 2005 — Spring 2008 with Seymour Grufferman, M.D., Dr. P.H. and Deirdre A. Hill, Ph.D., M.P.H. at the Cancer Research and Treatment Center, University of New Mexico, Albuquerque, NM 87131, USA. More results are likely to come from this rich dataset.
Erik Erhardt Research
On Jan 20th, 2009, I joined the Medical Image Analysis Laboratory (MIALab) as a research assistant (RA) at the MIND institute at UNM. This position will transition to a 2-3 year postdoc upon the completion of my PhD this May.
Read more…
Erik Erhardt MIND
Christopher P. Bickford, Nate G. Mcdowell, Erik Barry Erhardt, Heath H. Powers, David T. Hanson. (2009)
“High frequency field measurements of diurnal carbon isotope discrimination and internal conductance in a semi-arid species, Juniperus monosperma“.
Plant, Cell & Environment, In print (1/28/09).
Read more…
Erik Erhardt stable isotopes
I developed a solitaire game for pool (pocket billiards) that stresses the importance of making every shot count and developing your balls-per-inning potential for those of us who often run between 2 and 10 balls, based on straight pool. I call it “Penalized-x”, where “Penalized-5″ would specify 5 penalty balls. The rules:
Read more…
Erik Erhardt pool
I’m starting to dance again, after developing (2004ish) and having surgery (Dec 2006) to remove a Morton’s Neuroma in my left foot from dancing in beautiful shoes that were too narrow. It’s hard to find dance shoes in a 11-4E. To celebrate, here’s an contra I wrote some years ago, which I would love to call.
Read more…
Erik Erhardt dance
In high school I mostly played guitar, and in college I mostly composed music on the computer. Here’s a selection of that work.
Read more…
Erik Erhardt music
C MPI implementation of waves equation on 16 processors, init + 10 time steps.
Thanks to Matthew Bohnsack for setting my site up on wordpress. Matt and I worked together on projects in CS 442 Introduction to Parallel Processing in Fall 2006.
He’s hosted my site since April, 2007, and there have been terrific benefits. First, the server is beautifully configured and fast, and he’s given me plenty of space. Working with him has allowed me to provide my SISUS software prototype, which is an R package which I haven’t released, yet. He discusses his implementation of the software needed in his blog post. He is quick to respond, works meticulously, and understands the big picture as well as the individual pixels.
Erik Erhardt Fun