Erik Barry Erhardt, PhD

Wednesday, August 12th, 2009 exceeded my expectations in so many ways.  I was really touched by having so many people in attendance for my dissertation defense.  Friends and professors from math & stat, biology, and other departments, collaborators from the medical campus and from consulting outside the university, and my mom and brother.  About 25-30 in all.

My advisor, Edward Bedrick, provided a wonderful introduction that reminded me of the many ways I’ve connected with the UNM community: teaching (and awards), research assistantships (and publications), statistics department consultant, collaborations, and unicycling around campus those first few years.

I was generally happy with my presentation and was grateful that Ed reminded me occasionally of points that I wanted to make but had forgotten to mention.  He was also my champion whenever I tried to sell myself short, interjecting and saying that a particular point I was glossing over is nontrivial in theory and application.  I had some positive feedback and am learning how to give better talks.

My committee’s questions really helped me feel more like a peer, asking questions with the expectation that I might provide insight on a topic.  They never asked a question with the goal to stump me or make me feel small.  I felt supported, respected, encouraged, and welcomed into PhD family.

What next?  I’m now a postdoc at the Mind Research Network on the UNM campus in Albuquerque doing modeling for fMRI brain imaging data, see previous post.  I’m completing my dissertation to submit to the university, writing papers from the dissertation, and organizing work on my other collaborations.  These next couple years are going to challenging and exciting, frustrating and daunting, engaging and inspiring, and I’d better also say peaceful and tranquil so my mom thinks I’m getting some rest, too.  Carpe data!

Research

Dissertation defense for Erik Barry Erhardt, PhD candidate in Statistics
Wednesday, August 12th at 10am in Humanities 428
University of New Mexico

Title: Stable Isotope Sourcing using Sampling

Abstract:

Stable isotope sourcing is used to estimate proportional contributions of sources to a mixture, such as in the analysis of animal diets, plant nutrient use, geochemistry, pollution, and forensics. We focus on animal ecology because of the particular complexities due to the process of digestion and assimilation. Parameter estimation has been a challenge because there are often many sources and few isotopes leading to an underconstrained linear system for the diet probability vector. This dissertation off ers three primary contributions to the mixing model community. (1) We detail and provide an R implementation of a better algorithm (SISUS) for representing possible solutions in the underconstrained case (many sources, few isotopes) when no variance is considered (Phillips and Gregg, 2003). (2) We provide general methods for performing frequentist estimation in the perfectly-constrained case using the delta method and the bootstrap, which extends previous work applying the delta method to two- and three-source problems (Phillips and Gregg, 2001). (3) We propose two Bayesian models, the implicit representation model estimating the population mean diet through the mean mixture isotope ratio, and the explicit representation model estimating the population mean diet through mixture-specific diets given individual isotope ratios. Secondary contributions include (4) estimation using summaries from the literature in lieu of observation-level data, (5) multiple methods for incorporating isotope ratio discrimination (fractionation) in the analysis, (6) the use of measurement error to account for and partition more uncertainty, (7) estimation improvements by pooling multiple estimates, and (8) detailing scenarios when one model is preferred over another. We show that the Bayesian explicit representation model provides more precise diet estimates than other models when measurement error is small and informed by the necessary calibration measurements.

Research