<html><head><meta http-equiv="Content-Type" content="text/html charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">Hi everyone,</p><div class=""><font color="#111111" face="Helvetica Neue, Helvetica, Arial, Verdana, sans-serif" size="2" class="">I’m new to the working group, and by way of introduction wanted to pass along my short bio.</font></div><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">My research interests center around the application of Bayesian computational methods to addressing epidemiological problems. The first of these is in the modeling of the effectiveness of interventions in the control of infectious disease outbreaks. In particular, the goal is to estimate optimal policies for controlling outbreaks under uncertainty, and how information collected during the outbreak can be used to update the infornation state to improve future decisions, with an aim of reducing the severity or duration of the epidemic. Our approach for this involves constructing a joint model of the disease system using probabilistic modeling, whereby parameters associated with the susceptible population, the transmissiability and other characteristics of the pathogen, and the relative effects of the various intervention actions are included in a comprehensive model, and fit using Bayesian methods. This allows for the recreation of past epidemics, and the exploration of the likely effects of alternative intervention strategies, as well as the value of reducing uncertainty in relevant parameters of the disease system.</p><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">My second research focus is meta-analytic modeling for evidence-based medicine. We are often interested in the comparative effectiveness of biomedical interventions, usually for the treatment of illness or disease. For some conditions, for example, autism, heart disease or cancer, a large body of published literature amasses regarding the performance of candidate treatments, either in clinical trials or as larger population-based observational studies. However, conclusions from individual studies often do not generalize well outside the study population, and can often yield contradictory results from one another. In order to gain reliable inference regarding the relative efficacy of treatments, it is important to employ meta-analytic modeling methods to partially combine information across studies, in order to determine sub-populations or conditions for which some treatments are preferable to others. I apply Bayesian hierarchical models for evaluating comparative effectiveness across studies, because it allows information to be shared in a single analysis without completely pooling the information and ignoring heterogeneity. This paradigm allows multiple sources of independent information to be combined in a single analytic framework to provide information regarding a common set of parameters of interest.</p><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">An important aspect of my work is in the development of computational tools for Bayesian modeling. I have been a developer for the PyMC project since its introduction in 2003, a Python library for probabilistic programming. PyMC implements modern algorithms for fitting Baysian models, including Markov chain Monte Carlo and variational inference, and makes it easy for applied statisticians and modelers to implement arbitrary models, fit them, and analyze their outputs without having to hand-code algorithms.</p><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class=""><strong style="line-height: 1;" class="">Categories</strong>: epidemiology, decision analysis, meta-analysis</p><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class=""><strong style="line-height: 1;" class="">Methodologies</strong>: hierarchical models, Markov chain Monte Carlo, variational inference, reinforcement learning</p><h2 id="references" style="color: rgb(17, 17, 17); font-size: 20px; line-height: 42px; margin-top: 42px; margin-bottom: 21px; font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif;" class="">References</h2><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">Probert, W. J. M., Shea, K., Fonnesbeck, C. J., Runge, M. C., Carpenter, T. E., Dürr, S., et al. (2016). Decision-making for foot-and-mouth disease control: Objectives matter. <em style="line-height: 1;" class="">Epidemics</em>, <em style="line-height: 1;" class="">15</em>, 10–19. <a href="http://doi.org/10.1016/j.epidem.2015.11.002" class="">http://doi.org/10.1016/j.epidem.2015.11.002</a></p><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">Fonnesbeck, C. J., McPheeters, M. L., Krishnaswami, S., Lindegren, M. L., & Reimschisel, T. (2012). Estimating the probability of IQ impairment from blood phenylalanine for phenylketonuria patients: a hierarchical meta-analysis. <em style="line-height: 1;" class="">Journal of Inherited Metabolic Disease</em>, <em style="line-height: 1;" class="">36</em>(5), 757–766. <a href="http://doi.org/10.1007/s10545–012–9564–0" class="">http://doi.org/10.1007/s10545–012–9564–0</a></p><p style="color: rgb(17, 17, 17); font-family: 'Helvetica Neue', Helvetica, Arial, Verdana, sans-serif; word-wrap: break-word; margin: 1.3125em 0px; font-size: 1.1429em; line-height: 1.3125em;" class="">Salvatier, J., Wiecki, T. V., & Fonnesbeck, C. (2016). Probabilistic programming in Python using PyMC3. <em style="line-height: 1;" class="">PeerJ Computer Science</em>, <em style="line-height: 1;" class="">2</em>(2), e55. <a href="http://doi.org/10.7717/peerj-cs.55" class="">http://doi.org/10.7717/peerj-cs.55</a></p><div class="">
<div style="color: rgb(0, 0, 0); letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div style="color: rgb(0, 0, 0); letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div id="signature" class=""><div style="color: rgb(0, 0, 0); letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div class=""><div class="">--<br class=""></div><div class="">Chris Fonnesbeck<br class="">Assistant Professor of Biostatistics<br class="">Department of Biostatistics<br class="">Vanderbilt University Medical Center</div></div></div></div></div></div>
</div>
<br class=""></body></html>