<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 14 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
@font-face
{font-family:Consolas;
panose-1:2 11 6 9 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
pre
{mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0in;
margin-bottom:.0001pt;
font-size:10.0pt;
font-family:"Courier New";}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-priority:99;
mso-style-link:"HTML Preformatted";
font-family:"Consolas","serif";}
span.EmailStyle19
{mso-style-type:personal-reply;
font-family:"Calibri","sans-serif";
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri","sans-serif";}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="blue" vlink="purple">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:"Tahoma","sans-serif"">From:</span></b><span style="font-size:10.0pt;font-family:"Tahoma","sans-serif""> Richard Methot - NOAA Federal [mailto:richard.methot@noaa.gov]
<br>
<b>Sent:</b> Wednesday, July 24, 2013 11:35 AM<br>
<b>To:</b> Mark Maunder; Jim Ianelli - NOAA Federal; James Thorson - NOAA Federal; Allan Hicks - NOAA Federal; Ian Taylor - NOAA Federal; Athol Whitten<br>
<b>Subject:</b> seminar on INLA<o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<pre><span style="color:black">Dr. Janine Illian from the Centre for Research into Ecological and <o:p></o:p></span></pre>
<pre><span style="color:black">Environmental Modelling (CREEM) at the University of St. Andrews, UK <o:p></o:p></span></pre>
<pre><span style="color:black">will be visiting next week and has kindly agreed to give a NMML seminar <o:p></o:p></span></pre>
<pre><span style="color:black">(NMML conference room, Wednesday, July 31, at noon). I'll send out an <o:p></o:p></span></pre>
<pre><span style="color:black">email reminder next week, but hope you can join us. As Dr. Illian's <o:p></o:p></span></pre>
<pre><span style="color:black">topic is not limited to marine mammal applications, please feel free to <o:p></o:p></span></pre>
<pre><span style="color:black">forward this announcement to other NMFS/AFSC scientists who may be <o:p></o:p></span></pre>
<pre><span style="color:black">interested.<o:p></o:p></span></pre>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<div>
<p class="MsoNormal">FITTING COMPLEX MODELS IN INLA – DEVELOPMENTS AND EXTENSIONS<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">Integrated nested Laplace approximation (INLA) may be used to fit a <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">large class of (complex) statistical models. While MCMC methods use <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">stochastic simulations for estimation, integrated nested Laplace <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">approximation (INLA) is based on deterministic approximations where <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">there are no convergence issues. INLA is a very accurate and <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">computationally superior alternative to MCMC and may be used to fit a <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">large class of models, latent Gaussian models. Since INLA is fast, <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">complex modelling has become greatly facilitated and has also become <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">more accessible to non-specialists. In addition, due to the fact that <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">the fitting approach is embedded in a large and general class of <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">statistical models, very general types of models may be considered. This <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">allows us a lot more flexibility in the choice of model than previously <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">– and hence the models to capture interesting aspects of the data and <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">consequently the system they are relevant for. In the context of spatial <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">statistics, for example, we can now fit models to spatial point patterns <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">of high dimensionality, replicated point patterns, hierarchically marked <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">point patterns etc. In many cases, analysing these data sets with MCMC <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">approaches would be very cumbersome and computationally prohibitive. The <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">INLA-methodology has been implemented in C, and the associated numerical <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">calculations and algorithms rely on an efficient implementation of <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">numerical procedures for Gaussian Markov random fields (GMRF), in <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">particular the algorithms in the C-library GMRFLib. However, most users <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">do not need to worry about this, as the INLA-methodology has been made <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">accessible through a user-friendly R-library, R-INLA, described and <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">available for download at <a href="http://www.r-inla.org">www.r-inla.org</a>. Specifying and fitting models <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">using R-INLA is just as easy as applying standard routines in R, for <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">example fitting generalised linear models, and it also provides great <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">flexibility with regard to the models that may be fitted. In order to <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">illustrate INLA’s versatility I will discuss a range of spatial and <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">non-spatial examples and present a number of recent developments. This <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">concerns generalisations of the methodology as well as new functionality <o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">within the R-INLA library.<o:p></o:p></p>
</div>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<p class="MsoNormal">-- <br>
<b><span style="font-size:10.0pt;font-family:"Arial","sans-serif";color:#666666">Richard D. Methot Jr. Ph.D.</span></b><br>
<i><span style="font-size:10.0pt;font-family:"Arial","sans-serif";color:#666666">NOAA Fisheries -
</span></i><i><span style="font-family:"Arial","sans-serif";color:#666666">Science Advisor for Stock Assessments</span></i><o:p></o:p></p>
<div>
<p class="MsoNormal"><span style="font-size:10.0pt;font-family:"Arial","sans-serif";color:#666666">Office: 206-860-3365</span><br>
<span style="font-size:10.0pt;font-family:"Arial","sans-serif";color:#666666">Mobile: 301-787-0241</span><o:p></o:p></p>
</div>
</div>
</div>
</body>
</html>