added remainder of posts from wordpress

_posts/2009-09-23-a-much-better-template-heckerped.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: A much better template - Heckerped
+meta: 
+  _edit_last: "1"
+tags: 
+- Administrative
+layout: post
+---
+This template looks promising. I found it at <a title="imJTk.com" href="http://imjtk.com/" target="_blank">http://imjtk.com/</a> as a free template. The downsides are the first two links under blogroll and the attribution. Apparently for $35 I can get rid of these, but I think I will wait a bit longer to see if I like this template over all. One upside is that the header images seem easy to modify, but I don't have to worry about that initially since I actually like the images (except for the one I already deleted). 

_posts/2009-09-28-added-a-calendar.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: Added a calendar
+meta: 
+  _edit_last: "1"
+tags: 
+- Administrative
+layout: post
+---
+During my job interviews last winter, somebody mentioned they had created a professional google calendar. The purpose of this calendar was to ease the burden of scheduling appointments with students by allowing students to suggest a time when the instructor was available. I have done the same, although at the moment my free time is abundant. The calendar can be found <a title="My Professional Calendar" href="http://jaradniemi.com/blog/calendar/" target="_self">here</a>.

_posts/2009-09-30-all-models-are-wrong-but-some-are-useful.html

@@ -0,0 +1,14 @@
+--- 
+type: post
+status: publish
+published: true
+title: All models are wrong, but some are useful
+meta: 
+  _edit_last: "1"
+tags: 
+- Modeling
+layout: post
+---
+I was perusing <a>Bobby Gramacy's introductory slides</a> for his Bayesian Inference course here at UCSB. On slide 11, he mentions the saying "All models are wrong, but some are useful." Googling for this phrase, I found a <a href="http://www.stat.columbia.edu/~cook/movabletype/archives/2008/06/all_models_are.html">post</a> by Andrew Gelman about this phrase where he reiterates the point that all models are wrong and the goal of posterior model checking is "to understand what aspects of the data are captured by the model and what aspects are not."
+
+My addition to this conversation focuses on the second half of the saying. The fact that all models are wrong should not discourage anybody from trying to model in the first place. Instead, modelers need to understand what scientific question is being asked and build a model to answer that question. A model will be useful if it can answer the question of interest.

_posts/2009-10-01-google-wave.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: Google wave
+meta: 
+  _edit_last: "1"
+tags: 
+- Tools
+layout: post
+---
+<a title="Google wave" href="http://wave.google.com/" target="_blank">Google wave</a> is an in-development project that blurs the distinction between email, instant messaging, blogs, etc. It is meant as an online communication and collaboration tool. To incorporate this technology in the way we do work, it would great if the tool allowed users to mark up pdfs or images. I am only half-way through the video so perhaps it already does.

_posts/2009-10-02-kitchen-safe-digital-recipe-book.html

@@ -0,0 +1,16 @@
+--- 
+type: post
+status: publish
+published: true
+title: Kitchen-safe digital recipe book
+meta: 
+  _edit_last: "2"
+tags: []
+
+layout: post
+---
+I have had a few ideas for inventions. One of them is a digital recipe book with a touchscreen for navigation. Yesterday I decided to search to see if this product exists and sure enough it does. The <a href="http://www.mydemy.com/">Demy</a> is retailing for $300 and from their website
+
+<blockquote>The Demy is the first and only kitchen-safe digital recipe reader that will revolutionize the way you cook. The Demy holds your personal recipe collection in one compact, sleek device. Featuring a high-resolution color touchscreen, an uncluttered interface and many special tools to make any cook’s job easier.</blockquote>
+
+Good features include timers, measurement converters, and substitution suggestions. From reading the comments on amazon, it appears the Demy has a few problems to resolve including the inability to delete the default recipes and any cookbooks and tying the unit to a particular website. I would add to this that the Demy cannot be wall-mounted (as far as I can tell), no wifi, and cannot play music (streaming iTunes would be great). So although this is a step in the right direction it seems a bit pricey for what you get, still I'm happy somebody is working on the product.

_posts/2009-10-02-student-blogging.html

@@ -0,0 +1,17 @@
+--- 
+type: post
+status: publish
+published: true
+title: Student blogging
+meta: 
+  _edit_last: "2"
+tags: 
+- Modeling
+- PSTAT 262
+layout: post
+---
+<a title="First student post on aguanomics" href="http://aguanomics.com/2009/10/hong-kong-taxinomics.html" target="_blank">Here</a> is a post by a student in EEP100 at Berkeley on the <a title="Aguanomics" href="http://aguanomics.com/" target="_blank">aguanomics</a> blog. This is the first of a series of posts by students.
+
+I'm considering implementing this for my PSTAT 262MC class on Applied Bayesian Time Series. My thought is to require students to post twice during the quarter. The first post will try to forecast a time series using just intuition, i.e. no math/stats. The second post will try to forecast a time series (possibly the same one) using a statistical model based approach.
+
+Any thoughts?

_posts/2009-10-05-dealing-with-bibtex-files.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: dealing with bibTeX files
+meta: 
+  _edit_last: "1"
+tags: 
+- Tools
+layout: post
+---
+After reading <a href="http://xianblog.wordpress.com/2009/10/06/merging-bibtex-files/">this post</a> about merging bibTeX files, it reminded me of a program I used in the writing of my dissertation. The program, <a href="http://www.molspaces.com/cb2bib/">cb2Bib</a>, is a &ldquo;free, open source, and multiplatform application for rapidly extracting unformatted, or unstandardized bibliographic references from email alerts, journal Web pages, and PDF files.&rdquo; This program in addition to an institutional subscription to <a href="http://www.statindex.org/">statindex.org</a> helped tremendously in quickly incorporating references.

_posts/2009-10-05-qmss-ucsb.html

@@ -0,0 +1,17 @@
+--- 
+type: post
+status: publish
+published: true
+title: QMSS @ UCSB
+meta: 
+  _edit_last: "1"
+tags: 
+- Statistics
+- UCSB
+layout: post
+---
+To all Ph.D. students at the <a href="http://www.ucsb.edu/">University of California, Santa Barbara</a>, please check out the <a href="http://www.qmss.ucsb.edu/">quantitative methods in the social sciences</a> (QMSS) program. From the website:
+<blockquote>Quantitative Methods in the Social Sciences (QMSS) at UCSB is an interdisciplinary Ph.D. emphasis available to students who wish to develop and use cutting-edge quantitative methods in social science research. Our curriculum is designed to provide students with the rigorous mathematical and statistical background necessary for advanced quantitative work, while also providing a broad interdisciplinary perspective on the use of quantitative methods in the social sciences. A growing number of departments and faculty participate in the emphasis and our weekly colloquia, which features speakers engaged in quantitative research across all social science disciplines.</blockquote>
+I recommend any student interested in quantitative analysis in their field check out QMSS.
+
+<strong>Forecast:</strong> Students with a QMSS emphasis will be more marketable than their counterparts without it.

_posts/2009-10-07-another-reason-to-get-an-iphone.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: Another reason to get an iPhone
+meta: 
+  _edit_last: "1"
+tags: []
+
+layout: post
+---
+My current verizon contract is up and although I get a discount for being a UCSB employee, I'm not sure I want to continue with verizon. I like the idea of a do-everything device such as an iPhone or an android phone. This <a href="http://tech.slashdot.org/story/09/10/07/1133243/ATampT-To-Allow-VoIP-On-iPhone?from=rss">article</a> gives another reason to get an iPhone, namely AT&amp;T is going to allow VoIP over their data network. This would allow me to avoid the lack-of-minutes situation I am experiencing right now. (Tomorrow I will have all my minutes back.) My only hesitation here is that I would be doubling my monthly expense to get an iPhone plus data plan and I can't seem to justify it yet.

_posts/2009-10-08-meandering-river-video.html

@@ -0,0 +1,14 @@
+--- 
+type: post
+status: publish
+published: true
+title: Meandering river video
+meta: 
+  _edit_last: "1"
+tags: 
+- Science
+layout: post
+---
+I heard about this video on <a title="NPR" href="http://www.npr.org/" target="_blank">National Public Radio</a>'s <a title="Science Friday" href="http://www.sciencefriday.com/" target="_blank">Science Friday</a>.
+<object classid="clsid:d27cdb6e-ae6d-11cf-96b8-444553540000" width="320" height="255" codebase="http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0"><param name="flashvars" value="&amp;file=http://www.podtrac.com/pts/redirect.flv?http://media.libsyn.com/media/sciencefriday/river-100209.flv&amp;height=255&amp;width=320&amp;frontcolor=0xffffff&amp;backcolor=0xeeeecc&amp;lightcolor=0xFFFFFF&amp;showdigits=false&amp;autostart=false&amp;showicons=false&amp;usefullscreen=true&amp;wmode=opaque&amp;image=http://www.sciencefriday.com/video/videoicon/river.jpg&amp;callback=http://www.sciencefriday.com/test/vidstats.php&amp;id=10244&amp;showdownload=true&amp;link=http://www.podtrac.com/pts/redirect.mp4?http://media.libsyn.com/media/sciencefriday/river-100209.mp4" /><param name="src" value="http://www.sciencefriday.com/tools/players/mediaplayer.swf" /><param name="wmode" value="opaque" /><param name="allowfullscreen" value="true" /><embed type="application/x-shockwave-flash" width="320" height="255" src="http://www.sciencefriday.com/tools/players/mediaplayer.swf" allowfullscreen="true" wmode="opaque" flashvars="&amp;file=http://www.podtrac.com/pts/redirect.flv?http://media.libsyn.com/media/sciencefriday/river-100209.flv&amp;height=255&amp;width=320&amp;frontcolor=0xffffff&amp;backcolor=0xeeeecc&amp;lightcolor=0xFFFFFF&amp;showdigits=false&amp;autostart=false&amp;showicons=false&amp;usefullscreen=true&amp;wmode=opaque&amp;image=http://www.sciencefriday.com/video/videoicon/river.jpg&amp;callback=http://www.sciencefriday.com/test/vidstats.php&amp;id=10244&amp;showdownload=true&amp;link=http://www.podtrac.com/pts/redirect.mp4?http://media.libsyn.com/media/sciencefriday/river-100209.mp4"></embed></object>
+The video is of a mini meandering river constructed in a laboratory. Apparently this has been attempted for a hundred years without success. From a scientific perspective the question is what are the necessary components to allow/force a river to meander. The key ingredients are course and fine sediment as well as vegetation for bank strength. The findings are published <a title="Meandering river article" href="http://www.pnas.org/content/106/40/16936.abstract?sid=bf970e2d-ebf0-4452-8245-471ff061cebf" target="_blank">here</a> in the <a title="PNAS" href="http://www.pnas.org/" target="_blank">Proceedings for the National Academy of Sciences</a>.

_posts/2009-10-12-forecasting-datasets.html

@@ -0,0 +1,33 @@
+--- 
+type: post
+status: publish
+published: true
+title: Forecasting datasets
+meta: 
+  _edit_last: "1"
+tags: 
+- Datasets
+- PSTAT 262
+layout: post
+---
+As part my of PSTAT 262 (Applied Bayesian Time Series) next semester, I plan on having students pick out a data set to make both non-model and model based forecasts for the series. My only requirement for the data are that the correct forecasts cannot already exist.  An additional suggestion is that the forecasts come true soon so that forecasts can be compared with realizations.
+
+Examples of <strong>unacceptable</strong> datasets are
+<ul>
+	<li>Dow Jones Index from 1990-2000</li>
+	<li>Dollars spent on US health care until 2005</li>
+	<li>Abundance of passenger pigeons</li>
+</ul>
+Examples of <strong>acceptable</strong> datasets are
+<ul>
+	<li>Yearly average S&amp;P 500 Index from 1949 to present</li>
+	<li>Mean global temperature in the past millennium</li>
+	<li>Median U.S. House price for the past 40 years</li>
+</ul>
+Examples of <strong>ideal</strong> datasets are
+<ul>
+	<li>Daily price of Coca-Cola stock since 2000</li>
+	<li>Number of daily airline passengers for the past 5 years</li>
+	<li>Weekly sunspot activity since 1977</li>
+</ul>
+Students will be asked to forecast their time series at two different time points: a relatively short forecast and one relatively long.

_posts/2009-10-13-baltic-dry-index.html

@@ -0,0 +1,17 @@
+--- 
+type: post
+status: publish
+published: true
+title: Baltic Dry Index
+meta: 
+  _edit_last: "1"
+tags: 
+- Datasets
+- PSTAT 262
+layout: post
+---
+As mentioned in a previous <a href="http://jaradniemi.com/blog/2009/10/12/forecasting-datasets/">post</a>, I will be asking students in my PSTAT 262 class to choose and analyze a data set. I thought posting some suggestions on this blog would be a good way to introduce some possibilities.
+
+Shown below is a time series found at <a href="http://www.ritholtz.com/blog/2009/10/baltic-dry-index-2/">Barry Ritholtz's blog</a> which tracks the cost of moving goods via the sea.
+
+<img class="aligncenter" title="Baltic Dry Index" src="http://www.ritholtz.com/blog/wp-content/uploads/2009/10/10-9-09-BDI.gif" alt="" width="500" height="375" />

_posts/2009-10-13-economists-talk-climate-change-at-ucsb.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: Economists talk climate change at UCSB
+meta: 
+  _edit_last: "1"
+tags: 
+- Science
+layout: post
+---
+Oh man, I wish I had known about <a title="Economists talk climate change at UCSB" href="http://www.independent.com/news/2009/oct/12/economists-talk-climate-change-ucsb/" target="_blank">this</a> ahead of time.

_posts/2009-10-13-particle-mcmc-at-rss.html

@@ -0,0 +1,12 @@
+--- 
+type: post
+status: publish
+published: true
+title: Particle MCMC at RSS
+meta: 
+  _edit_last: "1"
+tags: 
+- Statistics
+layout: post
+---
+Tomorrow (14th Oct) at the Royal Statistical Society a <a title="Particle MCMC" href="http://www.rss.org.uk/main.asp?page=1836#Oct2009Meeting" target="_blank">paper is being read</a> entitled `Particle Markov chain Monte Carlo methods.' The <a title="Particle MCMC paper" href="http://www.rss.org.uk/pdf/Andrieu_et_al._14.10.09.pdf" target="_blank">paper</a> uses sequential Monte Carlo methods to provide a proposal for the joint distribution of latent states in a state-space model.

_posts/2009-10-14-debt-as-a-percentage-of-gdp.html

@@ -0,0 +1,15 @@
+--- 
+type: post
+status: publish
+published: true
+title: Debt as a percentage of GDP
+meta: 
+  _edit_last: "1"
+tags: 
+- Datasets
+- PSTAT 262
+layout: post
+---
+<a title="PSTAT 262 Datasets" href="http://jaradniemi.com/blog/2009/10/12/forecasting-datasets/" target="_self">Previously</a> I announced a plan to have students in my PSTAT 262 class model and forecast actual time series. Here is another example of a possible dataset for modeling which concerns US Debt from (almost) all sources as a percentage of GDP. As mentioned <a title="Link to original article" href="http://www.ritholtz.com/blog/2009/10/quarterly-review-and-outlook-q3-2009/" target="_blank">here</a>, this debt does not include a few trillion in “off balance sheet” financing, contingent unfunded pension plans for corporate and state and local governments, or unfunded liabilities of the U.S. government for such items as Medicare, Social Security and other programs.
+
+<img class="aligncenter" title="Debt as a percentage of GDP" src="http://www.investorsinsight.com/cfs-filesystemfile.ashx/__key/CommunityServer.Blogs.Components.WeblogFiles/john_5F00_mauldins_5F00_outside_5F00_the_5F00_box/jmotb101209image001_5F00_5BE06BA1.jpg" alt="" width="400" height="320" />

_posts/2009-10-15-all-space-missions-on-one-map.html

@@ -0,0 +1,14 @@
+--- 
+type: post
+status: publish
+published: true
+title: All space missions on one map
+meta: 
+  _edit_last: "1"
+tags: 
+- Science
+layout: post
+---
+This is a pretty cool figure.
+
+<a href="http://www.flickr.com/photos/adamcrowe/4002050596/sizes/o/"><img class="alignnone" title="All space missions on one map" src="http://farm3.static.flickr.com/2445/4002050596_0c2b6c4dd2_o.jpg" alt="" width="550" height="243" /></a>

_posts/2009-10-16-an-inconvenient-truth-graph.html

@@ -0,0 +1,15 @@
+--- 
+type: post
+status: publish
+published: true
+title: An inconvenient truth graph
+meta: 
+  _edit_last: "1"
+tags: 
+- Datasets
+- PSTAT 262
+layout: post
+---
+Ever since watching <a title="An inconvenient truth" href="http://www.climatecrisis.net/" target="_blank">An inconvenient truth</a>, I have wondered about this figure that shows an apparent relationship between carbon dioxide and global temperature.  I couldn't find a better version of this picture.
+
+<img class="aligncenter" title="Carbon dioxide - global temperature" src="http://farm1.static.flickr.com/167/380193705_4e21e9ea2a.jpg" alt="" width="500" height="358" />

_posts/2009-10-21-seminar-today.html

@@ -0,0 +1,13 @@
+--- 
+type: post
+status: publish
+published: true
+title: Seminar today
+meta: 
+  _edit_last: "1"
+tags: 
+- Statistics
+layout: post
+---
+I will be giving a seminar today in my department entitled `A sequential Monte Carlo primer.' The idea is to give those who are unfamiliar with the field an introduction. More can be read <a title="A sequential Monte Carlo primer" href="http://www.pstat.ucsb.edu/seminars.htm#Niemi" target="_blank">here</a> and obviously can be heard by coming to <span style="font-family: Verdana,Arial,Helvetica,sans-serif; font-size: x-small;">South Hall 5607F @ 3:15 PM, refreshments available at 3PM.
+</span>

_posts/2009-10-26-bioengineering-insights.html

@@ -0,0 +1,17 @@
+--- 
+type: post
+status: publish
+published: true
+title: Bioengineering insights
+meta: 
+  _edit_last: "1"
+tags: 
+- UCSB
+layout: post
+---
+I'm currently attending <a title="Bioengineering Insights 2009" href="http://engineering.ucsb.edu/insights2009/" target="_blank">Bioengineering Insights 2009</a>. It is a one-day conference on the interdisciplinary research effort at UCSB and with industry in the fields of biology, engineering, chemistry, physics and (with any luck) statistics. The opening keynote address was given by <a title="Lee Hood" href="http://www.systemsbiology.org/Scientists_and_Research/Faculty_Groups/Hood_Group" target="_blank">Lee Hood</a> of the <a title="Institute for Systems Biology" href="http://www.systemsbiology.org/" target="_blank">Institute for Systems Biology</a>. He gave an overview talk about the work his group is doing at ISB and where he believes medicine is headed in the future. In particular, promoted the idea of P4 medicine, where the P's stand for Predictive, Preventive, Personalized, and Participatory and more information can be found <a title="P4 Medicine" href="http://www.systemsbiology.org/Intro_to_ISB_and_Systems_Biology/Predictive_Preventive_Personalized_and_Participatory" target="_blank">here</a>.
+
+I attended Session A: Systems Biology this morning and learned alot about research going on at UCSB. The speakers were <a title="Linda Petzold" href="http://www.me.ucsb.edu/dept_site/people/new_faculty_pages/petzold_page.html" target="_blank">Linda Petzold</a>, <a title="Cherie Briggs" href="http://www.lifesci.ucsb.edu/eemb/faculty/briggs/" target="_blank">Cherie Briggs</a>,<a title="Jean Carlson" href="http://www.physics.ucsb.edu/~carlson/" target="_blank"> Jean Carlson</a>, <a title="Megan Valentine" href="http://www.me.ucsb.edu/valentinelab/index.html" target="_blank">Megan Valentine</a>, and <a title="David Low" href="http://www.lifesci.ucsb.edu/mcdb/faculty/low/" target="_blank">David Low</a>. In particular, I think my research would mesh well with Linda Petzold and her work on Post-traumatic stress disorder, Cherie Briggs and her SIR-type modeling of  fungal infections in frogs, or David Low and his Markov chain approach to understanding a 1kilobase pair region of the bacterial genome. Overall I thought Session A was full of exciting new research topics.
+
+<cite>
+</cite>