post59cc11d27a89.tmp.html

<div id="stephen-berg" class="section level2" number="0.1">
<h2><span class="header-section-number">0.1</span> Stephen Berg</h2>
<p><img src="department-photo.jpg" width="200"/></p>
</div>
<div id="about-me" class="section level2" number="0.2">
<h2><span class="header-section-number">0.2</span> About Me</h2>
<p>I am an assistant professor of statistics at Penn State University. I joined Penn State in 2020 after receiving my PhD in Statistics from the University of Wisconsin-Madison, where I was advised by Jun Zhu and Murray Clayton.</p>
<p>My research focuses on applications in spatial and spatial-temporal statistics, as well as on statistical computing problems, particularly related to Markov chain Monte Carlo (MCMC).</p>
<p><br /></p>
<p><strong>Statistical computing</strong></p>
<ul>
<li><p>My current work revolves around variance estimation and variance reduction for MCMC simulations.</p>
<ul>
<li>Recently I have worked with Hyebin Song at PSU on nonparametric variance estimation for reversible Markov chains, using tools similar to classic shape-constrained regression approaches like isotonic regression. <a href="https://arxiv.org/abs/2207.12705">Efficient shape-constrained inference for the autocovariance sequence from a reversible Markov chain</a></li>
<li>I am also interested in variance reduction for Markov chains using control variate and conditioning approaches. <a href="https://arxiv.org/abs/1912.06926">Control variates and Rao-Blackwellization for deterministic sweep Markov chains</a></li>
</ul></li>
</ul>
<p><br /></p>
<p><strong>Spatial-temporal statistics</strong></p>
<ul>
<li>I am interested in application problems in landscape ecology and in modeling chronic wasting disease (CWD) in Wisconsin deer, and in constructing realistic models of natural phenomena in order to do inference and forecasting. Methodologically, I am interested in differential equation and partial differential equation models, and addressing statistical and computational challenges for these models. <a href="https://doi.org/10.1214/19-AOAS1259">A latent discrete Markov random field approach to identifying and classifying historical forest communities based on spatial multivariate tree species counts</a></li>
<li>On the theory side, I am interested in using nonparametric tools to estimate spatial covariance functions.</li>
</ul>
<div id="research-opportunities" class="section level3" number="0.2.1">
<h3><span class="header-section-number">0.2.1</span> Research opportunities</h3>
<p>I have funding for motivated PhD students with an interest in statistical computing, spatial statistics, and/or nonparametric statistics problems. Please contact me by email to discuss potential research opportunities.</p>
<!-- `\begin{align*}\hat{\beta}=(X^\top X)^{-1}X^\top y\end{align*}` -->
<!-- ## _Keep it simple, but not simpler_ -->
<!-- **XMin** is a Hugo theme written by [Yihui Xie](https://yihui.org) in about four hours: half an hour was spent on the Hugo templates, and 3.5 hours were spent on styling. The main motivation for writing this theme was to provide a really minimal example to beginners of Hugo templates. This XMin theme contains about 130 lines of code in total, including the code in HTML templates and CSS (also counting empty lines). -->
<!-- ```{bash, comment='', echo=3, eval=Sys.which('bash') != '', message=FALSE} -->
<!-- cd ../..; -->
<!-- if [ ! -f 'theme.toml' ]; then exit 0; fi  # only run find below within the theme example site -->
<!-- find . -not -path '*/exampleSite/*' \( -name '*.html' -o -name '*.css' \) | xargs wc -l -->
<!-- ``` -->
<!-- I can certainly further reduce the code, for example, by eliminating the CSS, but I believe a tiny bit of CSS can greatly improve readability. You cannot really find many CSS frameworks that only contain 50 lines of code. -->
<!-- Although it is a minimal theme, it is actually fully functional. It supports pages (including the home page), blog posts, a navigation menu, categories, tags, and RSS. With [a little bit customization](https://github.com/yihui/hugo-xmin/blob/master/exampleSite/layouts/partials/foot_custom.html), it can easily support LaTeX math expressions, e.g., -->
<!-- `$${\sqrt {n}}\left(\left({\frac {1}{n}}\sum _{i=1}^{n}X_{i}\right)-\mu \right)\ {\xrightarrow {d}}\ N\left(0,\sigma ^{2}\right)$$` -->
<!-- All pages not under the root directory of the website are listed below. You can also visit the list page of a single section, e.g., [posts](/post/), or [notes](/note/). See the [About](/about/) page for the usage of this theme. -->
</div>
</div>