<?xml version="1.0" encoding="ISO-8859-1"?>
<!-- generator="FeedCreator 1.7.2" -->
<rss version="2.0">
    <channel>
        <title>INFORMS @ VT</title>
        <description>INFORMS @ VT Site Syndication</description>
        <link>http://www.informs.org.vt.edu</link>
        <lastBuildDate>Mon, 06 Oct 2008 07:43:50 +0100</lastBuildDate>
        <generator>FeedCreator 1.7.2</generator>
        <image>
            <url>http://www.informs.org.vt.edu/images/M_images/informs.jpg</url>
            <title>INFORMS VT Newsfeed</title>
            <link>http://www.informs.org.vt.edu</link>
            <description>INFORMS @ VT Site Syndication</description>
        </image>
        <item>
            <title>Coming up on September 10</title>
            <link>http://www.informs.org.vt.edu/index.php?option=com_content&amp;task=view&amp;id=259</link>
            <description>The INFORMS meeting this week will be held on &lt;strong&gt;Wednesday, September 10 at 12:20pm&lt;/strong&gt; in &lt;strong&gt;Durham 260&lt;/strong&gt; and will feature a presentation by &lt;strong&gt;Dr. Raghu Pasupathy&lt;/strong&gt; on &lt;strong&gt;Parameter Choice in Sample-path Algorithms for Root Finding and Optimization&lt;/strong&gt;.&lt;br /&gt;&lt;br /&gt;&lt;strong&gt;ABSTRACT&lt;/strong&gt;&lt;br /&gt;Retrospective Approximation (RA) is a sample-path technique for solving simulation-optimization and stochastic root-finding problems. RA works by generating and solving a sequence of deterministic problems, using specified sample-size and error-tolerance sequences. In this talk, we provide guidance on choosing these sequences by characterizing a class that is superior to others in a certain precisely defined sense. We provide numerical examples illustrating the key results.</description>
            <pubDate>Sun, 07 Sep 2008 22:53:39 +0100</pubDate>
        </item>
        <item>
            <title>Coming up on September 17</title>
            <link>http://www.informs.org.vt.edu/index.php?option=com_content&amp;task=view&amp;id=261</link>
            <description>The INFORMS meeting this week will be held on &lt;strong&gt;Wednesday, September 17 &lt;/strong&gt;at&lt;strong&gt; 12:15pm&lt;/strong&gt; in &lt;strong&gt;Durham 260&lt;/strong&gt; and will feature a presentation by &lt;strong&gt;Dr. Christopher F. Parmeter&lt;/strong&gt; on &lt;strong&gt;Constrained Nonparametric Kernel Regression: Estimation and Inference&lt;/strong&gt;.&lt;br /&gt;&lt;br /&gt;&lt;strong&gt;ABSTRACT&lt;/strong&gt;&lt;br /&gt;Restricted kernel regression methods have recently received much well-deserved attention. Powerful methods have been proposed for imposing monotonicity on the resulting estimate, a condition often dictated by theoretical concerns. However, to the best of our knowledge, there does not exist a simple yet general approach for constraining a nonparametric regression that allows practitioners to impose any manner and mix of constraints on the resulting estimate. We generalize Hall &amp; Huang's approach in order to allow for equality or inequality constraints on anonparametric regression model and its derivatives of any order. The proposed approach is straightforward, both conceptually and in practice. A testing framework is provided allowing researchers to thereby impose and test the validity of the restrictions. Illustrative Monte Carlo results are presented, and an application is considered.</description>
            <pubDate>Sun, 07 Sep 2008 22:53:39 +0100</pubDate>
        </item>
        <item>
            <title>Coming up on September 24</title>
            <link>http://www.informs.org.vt.edu/index.php?option=com_content&amp;task=view&amp;id=263</link>
            <description>The INFORMS meeting this week will be held on &lt;strong&gt;Wednesday, September 24 &lt;/strong&gt;at&lt;strong&gt; 12:15pm&lt;/strong&gt; in &lt;strong&gt;Durham 260&lt;/strong&gt; and will feature a presentation by &lt;strong&gt;Dr. Suqin Ge&lt;/strong&gt; on &lt;strong&gt;Accounting for Gender Gap in College Attainment&lt;/strong&gt;.&lt;br /&gt;&lt;br /&gt;&lt;strong&gt;ABSTRACT&lt;/strong&gt;&lt;br /&gt;One striking phenomenon in the U.S. labor market is the reversal of the gender gap in college attainment. Females have outnumbered males in college attainment since 1987. We develop a discrete choice model of college entry decisions to study the effects of changes in relative earnings, changes in parental education, and changes in the marriage market on time series observations of college attainment by gender. We find that the increasing relative earnings between college and high school individuals and increases in parental education have important effects on the increase in college attainment for both genders. The decrease in marriage rates is crucial in explaining the reversal of the gender gap in college attainment.</description>
            <pubDate>Sun, 07 Sep 2008 22:53:39 +0100</pubDate>
        </item>
        <item>
            <title>Coming up on October 1</title>
            <link>http://www.informs.org.vt.edu/index.php?option=com_content&amp;task=view&amp;id=276</link>
            <description>The INFORMS meeting this week will be held on &lt;strong&gt;Wednesday, October 1st &lt;/strong&gt;at&lt;strong&gt; 12:15pm&lt;/strong&gt; in &lt;strong&gt;Durham 260&lt;/strong&gt; and will feature a presentation by &lt;strong&gt;Dr. Joel A. Nachlas&lt;/strong&gt; on &lt;strong&gt;Operations Research and Operations Research at Virginia Tech&lt;/strong&gt;.&lt;br /&gt;&lt;br /&gt;&lt;strong&gt;ABSTRACT&lt;/strong&gt;&lt;br /&gt;A sketch of the history of Operations Research will be provided.  The associated evolution of the OR curriculum and faculty at Virginia Tech will be described.  Finally, the current ISE faculty aligned with OR will be enumerated along with a summary of their research interests.&lt;br /&gt;&lt;br /&gt;</description>
            <pubDate>Sun, 07 Sep 2008 22:53:39 +0100</pubDate>
        </item>
        <item>
            <title>Coming Up on November 28</title>
            <link>http://www.informs.org.vt.edu/index.php?option=com_content&amp;task=view&amp;id=257</link>
            <description>The INFORMS meeting this week, which will be held on &lt;strong&gt;Wednesday, November 28 at 12:20pm&lt;/strong&gt; in &lt;strong&gt;Durham 260&lt;/strong&gt;, will feature a presentation by &lt;strong&gt;Dr. Robert Gilles&lt;/strong&gt; on &lt;strong&gt;Building Social Networks&lt;/strong&gt;.&lt;br /&gt;&lt;br /&gt;&lt;strong&gt;ABSTRACT&lt;/strong&gt;&lt;br /&gt;&lt;blockquote&gt;&lt;div align=&quot;justify&quot;&gt;We examine the process of building social relationships as a non-cooperative game that requires mutual consent and involves reaching out to others at a cost. Players create their social network from amongst their set of acquaintances. Having acquaintances allows players to form naive beliefs about the feasibility of building direct relationships with their acquaintances. These myopic beliefs describe how the other players are expected to respond to the initiation of a link by a player. We introduce a stability concept called &quot;monadic stability&quot; where agents play a best response to their formed myopic beliefs such that these beliefs are self-confirming. The resulting equilibrium networks form subset of the set of pairwise stable networks.&lt;br /&gt;&lt;/div&gt;&lt;/blockquote&gt;&lt;br /&gt;</description>
            <pubDate>Wed, 28 Nov 2007 05:00:00 +0100</pubDate>
        </item>
    </channel>
</rss>
