<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (cshalizi)</title>
    <link>https://pinboard.in/u:cshalizi/public/</link>
    <description>recent bookmarks from cshalizi</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.sketchingbigdata.org/fall20/lec/notes.pdf"/>
	<rdf:li rdf:resource="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3444678"/>
	<rdf:li rdf:resource="https://statisticalatlas.com/United-States/Overview"/>
	<rdf:li rdf:resource="https://www.usenix.org/sites/default/files/conference/protected-files/atc16_cantrill_slides.pdf"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/05/26/055624"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1604.00289"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1502.04585"/>
	<rdf:li rdf:resource="http://dx.doi.org/10.1126/science.1229566"/>
	<rdf:li rdf:resource="http://www.theawl.com/2015/06/a-complete-taxonomy-of-internet-chum"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1411.2664"/>
	<rdf:li rdf:resource="http://gking.harvard.edu/files/gking/files/multi.pdf"/>
	<rdf:li rdf:resource="http://www.crcpress.com/product/isbn/9781466508910/des"/>
	<rdf:li rdf:resource="http://genome.cshlp.org/content/17/6/669.full"/>
	<rdf:li rdf:resource="http://www.andrewalexanderprice.com/blog20131204.php"/>
	<rdf:li rdf:resource="http://www.newyorker.com/reporting/2014/06/23/140623fa_fact_lepore?currentPage=all"/>
	<rdf:li rdf:resource="http://www.nature.com/ng/journal/v44/n6/abs/ng.2285.html"/>
	<rdf:li rdf:resource="http://www.genetics.org/content/155/2/945.short"/>
	<rdf:li rdf:resource="http://paintmychromosomes.blogspot.com/2014/06/what-did-we-learn-from-rosenberg-et-al.html"/>
	<rdf:li rdf:resource="https://medium.com/technology-and-society/2f1fe84c5c9b"/>
	<rdf:li rdf:resource="http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2326746"/>
	<rdf:li rdf:resource="http://www.heracliteanriver.com/?p=324"/>
	<rdf:li rdf:resource="http://www.nature.com/nature/journal/vaop/ncurrent/full/nature11867.html"/>
	<rdf:li rdf:resource="http://delong.typepad.com/sdj/2012/11/war-on-nate-silver-final-after-action-report-the-flag-of-science-flies-uncontested-over-silvergrad-weblogging.html"/>
	<rdf:li rdf:resource="http://www.tnr.com/article/books-and-arts/magazine/105703/the-naked-and-the-ted-khanna"/>
	<rdf:li rdf:resource="http://lingpipe-blog.com/2012/05/29/averages-vs-means/"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1203.3504"/>
	<rdf:li rdf:resource="http://httpcats.herokuapp.com/"/>
	<rdf:li rdf:resource="http://www-stat.stanford.edu/~tibs/ElemStatLearn/"/>
	<rdf:li rdf:resource="http://benfry.com/writing/archives/571"/>
	<rdf:li rdf:resource="http://www.jstor.org/stable/4175421"/>
	<rdf:li rdf:resource="http://www.jstor.org/stable/20009633"/>
	<rdf:li rdf:resource="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0006777"/>
	<rdf:li rdf:resource="http://homepages.cwi.nl/~lex/files/histtrpclean.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0905.3369"/>
	<rdf:li rdf:resource="http://www.cs.berkeley.edu/~brewer/papers/SearchDB.pdf"/>
	<rdf:li rdf:resource="http://www.zylstra.org/blog/archives/2009/05/wolframalpha_ge.html"/>
	<rdf:li rdf:resource="http://messymatters.com/2009/03/21/the-future-is-yesterday/"/>
	<rdf:li rdf:resource="http://www.nbc.com/Saturday_Night_Live/video/clips/sloths/61792/"/>
	<rdf:li rdf:resource="http://norvig.com/fact-check.html"/>
	<rdf:li rdf:resource="http://differ.raysend.com/sex-differences-in-iq-variabil-0"/>
	<rdf:li rdf:resource="http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.1533"/>
	<rdf:li rdf:resource="http://www.cog.brown.edu/~mj/papers/JohnsonGriffithsGoldwater06AdaptorGrammars.pdf"/>
	<rdf:li rdf:resource="http://pipeline.corante.com/archives/2009/01/19/ten_years_after_the_genomics_frenzy.php"/>
	<rdf:li rdf:resource="http://www.cs.uwaterloo.ca/~mackerma/ClusteringQualityPaper.pdf"/>
	<rdf:li rdf:resource="http://radfordneal.wordpress.com/"/>
	<rdf:li rdf:resource="http://www.powells.com/review/2008_08_14.html"/>
	<rdf:li rdf:resource="http://www.qwantz.com/archive/000767.html"/>
	<rdf:li rdf:resource="http://www.nature.com/ng/journal/v40/n5/abs/ng.139.html"/>
	<rdf:li rdf:resource="http://xkcd.com/231/"/>
	<rdf:li rdf:resource="http://www.slate.com/id/2081746/"/>
	<rdf:li rdf:resource="http://www.lecun.org/gallery/libpro/20011121-allyourbayes/index.html"/>
	<rdf:li rdf:resource="http://www.efalken.com/papers/VaR.PDF"/>
	<rdf:li rdf:resource="http://www.stat.columbia.edu/~gelman/research/unpublished/multiple2.pdf"/>
	<rdf:li rdf:resource="http://econpapers.repec.org/paper/nbrnberwo/12632.htm"/>
	<rdf:li rdf:resource="http://www.tnr.com/story_print.html?id=d6977c2f-4788-468e-8f63-2e92109320fe"/>
	<rdf:li rdf:resource="http://dbpubs.stanford.edu/~klein/lagrange-multipliers.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0711.0194"/>
	<rdf:li rdf:resource="http://cg.scs.carleton.ca/~luc/rnbookindex.html"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.sketchingbigdata.org/fall20/lec/notes.pdf">
    <title>Sketching Algorithms</title>
    <dc:date>2022-02-23T14:45:07+00:00</dc:date>
    <link>https://www.sketchingbigdata.org/fall20/lec/notes.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to:NB computational_statistics theoretical_computer_science random_projections compressed_sensing linear_algebra to_read via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:89dce5b64027/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:theoretical_computer_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_projections"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:compressed_sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_algebra"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3444678">
    <title>Observational vs Experimental Data When Making Automated Decisions Using Machine Learning by Carlos Fernández-Loría, Foster Provost :: SSRN</title>
    <dc:date>2021-05-08T13:17:33+00:00</dc:date>
    <link>https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3444678</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["With the recent explosion in both data and computing power, machine learning algorithms are increasingly used to make decisions automatically. These decisions are often causal in nature with the goal of improving an outcome by means of an intervention. Common examples include influencing someone's purchasing behavior with an advertisement or increasing customer retention with a special offer. Unfortunately, if these algorithms use observational data to estimate the effect of the interventions, the resulting estimates will likely suffer from confounding bias. Investing in experimental data offers a way to estimate effects without confounding bias, but such data are costly and may be in short supply. This paper addresses the question of whether it would be better to invest in costly experimental data or use the readily-available (but confounded) observational data. We present a theoretical comparison between the use of observational and experimental data when the goal is to build models to make automated intervention decisions. The key insight of the work is that optimizing to make the correct decision generally involves understanding whether a causal effect is above or below a given threshold, which is different from optimizing to reduce the magnitude of the bias in a causal-effect estimate. As a result, models trained with confounded observational data may lead to decisions that are just as good (or better) in certain scenarios, such as when larger causal effects are more likely to be overestimated or when the benefits of larger and cheaper data outweigh the detrimental effect of confounding. The theoretical results are tested by comparing the two approaches using the wide variety of benchmark data sets (7,700 in total) from the 2016 ACIC causal modeling competition. Finally, we suggest that sensitivity analysis may be used in practice to determine whether collecting experimental data to improve treatment assignments would be cost-effective, illustrating with a simple procedure that shows a ``Goldilocks effect'': in the illustration, the size of the experiment has to be just right for the investment to be worthwhile."]]></description>
<dc:subject>to:NB causal_inference experimental_design decision_theory via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:104863fd3ea6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:experimental_design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:decision_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://statisticalatlas.com/United-States/Overview">
    <title>The Demographic Statistical Atlas of the United States - Statistical Atlas</title>
    <dc:date>2020-09-28T15:03:43+00:00</dc:date>
    <link>https://statisticalatlas.com/United-States/Overview</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>visual_display_of_quantitative_information demography via:arthegall to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cd5c089755d4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:visual_display_of_quantitative_information"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:demography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.usenix.org/sites/default/files/conference/protected-files/atc16_cantrill_slides.pdf">
    <title>A Wardrobe for the Emperor</title>
    <dc:date>2016-09-09T13:27:56+00:00</dc:date>
    <link>https://www.usenix.org/sites/default/files/conference/protected-files/atc16_cantrill_slides.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>why_oh_why_cant_we_have_a_better_academic_publishing_system computer_science via:arthegall have_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:85561293099a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_academic_publishing_system"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computer_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/05/26/055624">
    <title>Could a neuroscientist understand a microprocessor? | bioRxiv</title>
    <dc:date>2016-05-27T03:26:24+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/05/26/055624</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["There is a popular belief in neuroscience that we are primarily data limited, that producing large, multimodal, and complex datasets will, enabled by data analysis algorithms, lead to fundamental insights into the way the brain processes information. Microprocessors are among those artificial information processing systems that are both complex and that we understand at all levels, from the overall logical flow, via logical gates, to the dynamics of transistors. Here we take a simulated classical microprocessor as a model organism, and use our ability to perform arbitrary experiments on it to see if popular data analysis methods from neuroscience can elucidate the way it processes information. We show that the approaches reveal interesting structure in the data but do not meaningfully describe the hierarchy of information processing in the processor. This suggests that current approaches in neuroscience may fall short of producing meaningful models of the brain."]]></description>
<dc:subject>to:NB neuroscience have_read neural_data_analysis via:arthegall satire</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:de8e99bc7729/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neuroscience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:satire"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1604.00289">
    <title>[1604.00289] Building Machines That Learn and Think Like People</title>
    <dc:date>2016-05-14T01:37:48+00:00</dc:date>
    <link>https://arxiv.org/abs/1604.00289</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models."]]></description>
<dc:subject>cognitive_science artificial_intelligence neural_networks machine_learning via:arthegall gershman.samuel tenenbaum.joshua in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:56aa94704375/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cognitive_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:artificial_intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gershman.samuel"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tenenbaum.joshua"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1502.04585">
    <title>[1502.04585] The Ladder: A Reliable Leaderboard for Machine Learning Competitions</title>
    <dc:date>2016-04-25T16:58:57+00:00</dc:date>
    <link>http://arxiv.org/abs/1502.04585</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The organizer of a machine learning competition faces the problem of maintaining an accurate leaderboard that faithfully represents the quality of the best submission of each competing team. What makes this estimation problem particularly challenging is its sequential and adaptive nature. As participants are allowed to repeatedly evaluate their submissions on the leaderboard, they may begin to overfit to the holdout data that supports the leaderboard. Few theoretical results give actionable advice on how to design a reliable leaderboard. Existing approaches therefore often resort to poorly understood heuristics such as limiting the bit precision of answers and the rate of re-submission. 
"In this work, we introduce a notion of "leaderboard accuracy" tailored to the format of a competition. We introduce a natural algorithm called "the Ladder" and demonstrate that it simultaneously supports strong theoretical guarantees in a fully adaptive model of estimation, withstands practical adversarial attacks, and achieves high utility on real submission files from an actual competition hosted by Kaggle. 
"Notably, we are able to sidestep a powerful recent hardness result for adaptive risk estimation that rules out algorithms such as ours under a seemingly very similar notion of accuracy. On a practical note, we provide a completely parameter-free variant of our algorithm that can be deployed in a real competition with no tuning required whatsoever."

--- Basically, return the new score if, but only if, the new submission beats the previous best by some threshold.  I think this blocks my "flood with models" attack...]]></description>
<dc:subject>learning_theory cross-validation have_read via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b2bafec2bfe3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://dx.doi.org/10.1126/science.1229566">
    <title>Identifying Personal Genomes by Surname Inference | Science</title>
    <dc:date>2016-03-15T22:12:19+00:00</dc:date>
    <link>http://dx.doi.org/10.1126/science.1229566</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Sharing sequencing data sets without identifiers has become a common practice in genomics. Here, we report that surnames can be recovered from personal genomes by profiling short tandem repeats on the Y chromosome (Y-STRs) and querying recreational genetic genealogy databases. We show that a combination of a surname with other types of metadata, such as age and state, can be used to triangulate the identity of the target. A key feature of this technique is that it entirely relies on free, publicly accessible Internet resources. We quantitatively analyze the probability of identification for U.S. males. We further demonstrate the feasibility of this technique by tracing back with high probability the identities of multiple participants in public sequencing projects."]]></description>
<dc:subject>to:NB privacy genetics statistics via:arthegall genomics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:aadd34786d28/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genomics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.theawl.com/2015/06/a-complete-taxonomy-of-internet-chum">
    <title>A Complete Taxonomy of Internet Chum - The Awl</title>
    <dc:date>2015-06-06T21:38:11+00:00</dc:date>
    <link>http://www.theawl.com/2015/06/a-complete-taxonomy-of-internet-chum</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>advertising networked_life internet cultural_criticism via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b4c21e5d6d3c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:advertising"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networked_life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:internet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cultural_criticism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1411.2664">
    <title>[1411.2664] Preserving Statistical Validity in Adaptive Data Analysis</title>
    <dc:date>2015-01-30T14:55:34+00:00</dc:date>
    <link>http://arxiv.org/abs/1411.2664</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A great deal of effort has been devoted to reducing the risk of spurious scientific discoveries, from the use of sophisticated validation techniques, to deep statistical methods for controlling the false discovery rate in multiple hypothesis testing. However, there is a fundamental disconnect between the theoretical results and the practice of data analysis: the theory of statistical inference assumes a fixed collection of hypotheses to be tested, or learning algorithms to be applied, selected non-adaptively before the data are gathered, whereas in practice data is shared and reused with hypotheses and new analyses being generated on the basis of data exploration and the outcomes of previous analyses. 
"In this work we initiate a principled study of how to guarantee the validity of statistical inference in adaptive data analysis. As an instance of this problem, we propose and investigate the question of estimating the expectations of m adaptively chosen functions on an unknown distribution given n random samples. 
"We show that, surprisingly, there is a way to estimate an \emph{exponential} in n number of expectations accurately even if the functions are chosen adaptively. This gives an exponential improvement over standard empirical estimators that are limited to a linear number of estimates. Our result follows from a general technique that counter-intuitively involves actively perturbing and coordinating the estimates, using techniques developed for privacy preservation. We give additional applications of this technique to our question."]]></description>
<dc:subject>to_read statistics learning_theory via:arthegall concentration_of_measure stability_of_learning in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:566b354de5be/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stability_of_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://gking.harvard.edu/files/gking/files/multi.pdf">
    <title>A Theory of Statistical Inference for Matching Methods in Applied Causal Research</title>
    <dc:date>2015-01-09T14:00:11+00:00</dc:date>
    <link>http://gking.harvard.edu/files/gking/files/multi.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Applied researchers use matching methods for causal inference most commonly as a data preprocessing step for reducing model dependence and bias, after which they use whatever statistical model and uncertainty estimators they would have without matching, such as a difference in means or regression. They also routinely ignore the requirement of existing theory that all matches be exact, and also commonly use ad hoc analyses with iterations between formal matching methods and informal balance checks. We offer the first comprehensive theory of statistical inference to justify these widely used procedures. The theory we propose is substantively plausible, requires no asymptotic theory, and is simple to understand. Its core conceptualizes continuous variables as having natural breakpoints, which are common in applications (e.g., high school or college degrees in years of education, a governmental poverty level in in- come, or phase transitions in temperature). The theory allows binary, multicategory, and continuous treatment variables from the outset and straightforward extensions for imperfect treatment assignment and different versions of treatments. Although this theory provides a valid foundation for most commonly used methods of matching, researchers must still satisfy the assumptions in any real application."]]></description>
<dc:subject>to:NB causal_inference statistics king.gary via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5be82af92a4a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:king.gary"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.crcpress.com/product/isbn/9781466508910/des">
    <title>Visualization Analysis and Design - CRC Press Book</title>
    <dc:date>2015-01-02T18:10:47+00:00</dc:date>
    <link>http://www.crcpress.com/product/isbn/9781466508910/des</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Visualization Analysis and Design provides a systematic, comprehensive framework for thinking about visualization in terms of principles and design choices. The book features a unified approach encompassing information visualization techniques for abstract data, scientific visualization techniques for spatial data, and visual analytics techniques for interweaving data transformation and analysis with interactive visual exploration. It emphasizes the careful validation of effectiveness and the consideration of function before form.
"The book breaks down visualization design according to three questions: what data users need to see, why users need to carry out their tasks, and how the visual representations proposed can be constructed and manipulated. It walks readers through the use of space and color to visually encode data in a view, the trade-offs between changing a single view and using multiple linked views, and the ways to reduce the amount of data shown in each view. The book concludes with six case studies analyzed in detail with the full framework.
"The book is suitable for a broad set of readers, from beginners to more experienced visualization designers. It does not assume any previous experience in programming, mathematics, human–computer interaction, or graphic design and can be used in an introductory visualization course at the graduate or undergraduate level."]]></description>
<dc:subject>to:NB books:noted visual_display_of_quantitative_information design via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:14e3ecee8f51/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:noted"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:visual_display_of_quantitative_information"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://genome.cshlp.org/content/17/6/669.full">
    <title>What is a gene, post-ENCODE? History and updated definition</title>
    <dc:date>2014-08-14T16:03:25+00:00</dc:date>
    <link>http://genome.cshlp.org/content/17/6/669.full</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["While sequencing of the human genome surprised us with how many protein-coding genes there are, it did not fundamentally change our perspective on what a gene is. In contrast, the complex patterns of dispersed regulation and pervasive transcription uncovered by the ENCODE project, together with non-genic conservation and the abundance of noncoding RNA genes, have challenged the notion of the gene. To illustrate this, we review the evolution of operational definitions of a gene over the past century—from the abstract elements of heredity of Mendel and Morgan to the present-day ORFs enumerated in the sequence databanks. We then summarize the current ENCODE findings and provide a computational metaphor for the complexity. Finally, we propose a tentative update to the definition of a gene: A gene is a union of genomic sequences encoding a coherent set of potentially overlapping functional products. Our definition sidesteps the complexities of regulation and transcription by removing the former altogether from the definition and arguing that final, functional gene products (rather than intermediate transcripts) should be used to group together entities associated with a single gene. It also manifests how integral the concept of biological function is in defining genes."]]></description>
<dc:subject>to:NB biology bioinformatics genetics gene_expression_data_analysis gene_regulation have_read via:arthegall molecular_biology</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bdbc118e587f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gene_expression_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gene_regulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:molecular_biology"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.andrewalexanderprice.com/blog20131204.php">
    <title>A Traditional City Primer</title>
    <dc:date>2014-07-28T19:31:44+00:00</dc:date>
    <link>http://www.andrewalexanderprice.com/blog20131204.php</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Look, the eye-candy is great, but let's get real.  There were very powerful drives towards very large cities, in the form of economies of scale in production and infrastructure, and economies of agglomeration.  At the same time, living in a city of great size (say > 500k, a huge metropolis by pre-modern standards) without transit sucks.  Renaissance Florence --- a "traditional city" --- was counted very large at ~100k, or even ~70k, during its peak of prominence.  This is smaller than a modern college town like Ann Arbor or Madison, and comparable to a resort town like Santa Fe.  Show me this scaling up to even half a million and we'll talk.]]></description>
<dc:subject>cities urbanism design architecture via:arsyed have_read nostalgia via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:414298b353ce/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:urbanism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arsyed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nostalgia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.newyorker.com/reporting/2014/06/23/140623fa_fact_lepore?currentPage=all">
    <title>Jill Lepore: What the Theory of “Disruptive Innovation” Gets Wrong : The New Yorker</title>
    <dc:date>2014-06-17T03:07:57+00:00</dc:date>
    <link>http://www.newyorker.com/reporting/2014/06/23/140623fa_fact_lepore?currentPage=all</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[- This actually seems like a good example of Boudon's theory of ideology.  It's not enough for the ideology to have moral/political content.  To be effective, it has to also have some story about how the world works which _makes sense_ (you can see how things _could_ happen that way), and fits some examples, or seems to.  The ideologist then over-generalizes (becomes what Boudon calls a "hyperbole machine").]]></description>
<dc:subject>innovation our_decrepit_institutions why_corporations_are_messed_up the_wired_ideology evisceration lepore.jill have_read via:arthegall economic_history natural_history_of_truthiness ideology to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:152f730e1057/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:innovation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:our_decrepit_institutions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_corporations_are_messed_up"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_wired_ideology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:evisceration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lepore.jill"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:economic_history"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_history_of_truthiness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ideology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nature.com/ng/journal/v44/n6/abs/ng.2285.html">
    <title>A model-based approach for analysis of spatial structure in genetic data : Nature Genetics : Nature Publishing Group</title>
    <dc:date>2014-06-09T19:28:17+00:00</dc:date>
    <link>http://www.nature.com/ng/journal/v44/n6/abs/ng.2285.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Characterizing genetic diversity within and between populations has broad applications in studies of human disease and evolution. We propose a new approach, spatial ancestry analysis, for the modeling of genotypes in two- or three-dimensional space. In spatial ancestry analysis (SPA), we explicitly model the spatial distribution of each SNP by assigning an allele frequency as a continuous function in geographic space. We show that the explicit modeling of the allele frequency allows individuals to be localized on the map on the basis of their genetic information alone. We apply our SPA method to a European and a worldwide population genetic variation data set and identify SNPs showing large gradients in allele frequency, and we suggest these as candidate regions under selection. These regions include SNPs in the well-characterized LCT region, as well as at loci including FOXP2, OCA2 and LRP1B."]]></description>
<dc:subject>genetics historical_genetics statistics spatial_statistics via:arthegall in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e59de8e990e1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:historical_genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spatial_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.genetics.org/content/155/2/945.short">
    <title>Inference of Population Structure Using Multilocus Genotype Data</title>
    <dc:date>2014-06-08T12:10:19+00:00</dc:date>
    <link>http://www.genetics.org/content/155/2/945.short</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["arthegall" is right, this is "just" LDA applied to alleles instead of words.  (Or, considering publication dates, LDA is "just" STRUCTURE.)  Note that the algorithm _presumes_ the existence of K discrete populations.  None of the simulations look at what happens when, say, each point in space has its own distribution of genotypes, but those distributions vary continuously...]]></description>
<dc:subject>to:NB genetics have_read clustering statistics to_teach:data-mining historical_genetics via:arthegall latent_dirichlet_allocation topic_models to:blog</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c38b295faa36/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:historical_genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:latent_dirichlet_allocation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:topic_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://paintmychromosomes.blogspot.com/2014/06/what-did-we-learn-from-rosenberg-et-al.html">
    <title>What did we learn from Rosenberg et al. 2002, actually? | Ancestry matters</title>
    <dc:date>2014-06-04T12:35:44+00:00</dc:date>
    <link>http://paintmychromosomes.blogspot.com/2014/06/what-did-we-learn-from-rosenberg-et-al.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Really, LDA?]]></description>
<dc:subject>historical_genetics clustering statistics to_teach:data-mining to_teach:undergrad-ADA via:arthegall track_down_references latent_dirichlet_allocation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:eb60732ffe45/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:historical_genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:track_down_references"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:latent_dirichlet_allocation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://medium.com/technology-and-society/2f1fe84c5c9b">
    <title>No, Nate, brogrammers may not be macho, but that’s not all there is to it — Technology and Society — Medium</title>
    <dc:date>2014-03-27T19:35:31+00:00</dc:date>
    <link>https://medium.com/technology-and-society/2f1fe84c5c9b</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>institutions nerdworld geekdom sexism have_read cultural_capital via:arthegall to:blog tufekci.zeynep</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0fe356406409/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:institutions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nerdworld"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:geekdom"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sexism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cultural_capital"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tufekci.zeynep"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2326746">
    <title>Fool's Gold: an Illustrated Critique of Differential Privacy by Jane R. Bambauer, Krish Muralidhar, Rathindra Sarathy :: SSRN</title>
    <dc:date>2013-09-26T17:32:02+00:00</dc:date>
    <link>http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2326746</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Differential privacy has taken the privacy community by storm. Computer scientists developed this technique to allow researchers to submit queries to databases without being able to glean sensitive information about the individuals described in the data. Legal scholars champion differential privacy as a practical solution to the competing interests in research and confidentiality, and policymakers are poised to adopt it as the gold standard for data privacy. It would be a disastrous mistake. 
"This Article provides an illustrated guide to the virtues and pitfalls of differential privacy. While the technique is suitable for a narrow set of research uses, the great majority of analyses would produce results that are beyond absurd: average income in the negative millions, or correlations well above 1, for example. 
"The legal community has been misled into thinking that differential privacy can offer the benefits of data research without sacrificing privacy. In fact, differential privacy will usually produce either very wrong research results or very useless privacy protections. Policymakers and data stewards will have to rely on a mix of approaches: perhaps differential privacy where it is well-suited to the task, and other disclosure prevention techniques in the great majority of situations where it isn’t."

--- All of the strength of the argument here comes from getting _very_ large values for the sensitivity of the statistics to perturbations, and it seems somewhat bizarre to insist that one first look at the sensitivity of a total when the real goal is an average.  I emerge dubious both of the authors and of differential privacy.]]></description>
<dc:subject>data_mining statistics privacy differential_privacy via:arthegall have_read to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3fac6685fd11/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:differential_privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.heracliteanriver.com/?p=324">
    <title>Why two spaces after a period isn’t wrong (or, the lies typographers tell about history) - Heraclitean River</title>
    <dc:date>2013-05-24T14:07:05+00:00</dc:date>
    <link>http://www.heracliteanriver.com/?p=324</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[The quotes from the earlier editions of the Chicago Manual are particularly nice.]]></description>
<dc:subject>typography debunking evisceration historical_myths via:arthegall have_read to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8366524130a9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:typography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:debunking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:evisceration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:historical_myths"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nature.com/nature/journal/vaop/ncurrent/full/nature11867.html">
    <title>Finding the sources of missing heritability in a yeast cross : Nature : Nature Publishing Group</title>
    <dc:date>2013-02-07T17:15:39+00:00</dc:date>
    <link>http://www.nature.com/nature/journal/vaop/ncurrent/full/nature11867.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["For many traits, including susceptibility to common diseases in humans, causal loci uncovered by genetic-mapping studies explain only a minority of the heritable contribution to trait variation. Multiple explanations for this ‘missing heritability’ have been proposed1. Here we use a large cross between two yeast strains to accurately estimate different sources of heritable variation for 46 quantitative traits, and to detect underlying loci with high statistical power. We find that the detected loci explain nearly the entire additive contribution to heritable variation for the traits studied. We also show that the contribution to heritability of gene–gene interactions varies among traits, from near zero to approximately 50 per cent. Detected two-locus interactions explain only a minority of this contribution. These results substantially advance our understanding of the missing heritability problem and have important implications for future studies of complex and quantitative traits."]]></description>
<dc:subject>to:NB genetics yeast heritability variance_estimation via:arthegall re:g_paper</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:afa983e16cfa/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:yeast"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heritability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:variance_estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:g_paper"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://delong.typepad.com/sdj/2012/11/war-on-nate-silver-final-after-action-report-the-flag-of-science-flies-uncontested-over-silvergrad-weblogging.html">
    <title>Brad DeLong: War on Nate Silver: Final After-Action Report: The Flag of Reality Flies Uncontested Over Silvergrad Weblogging</title>
    <dc:date>2012-11-20T15:45:39+00:00</dc:date>
    <link>http://delong.typepad.com/sdj/2012/11/war-on-nate-silver-final-after-action-report-the-flag-of-science-flies-uncontested-over-silvergrad-weblogging.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[I am, of course, quite serious about the to_teach tag.  Better reactionaries, please.]]></description>
<dc:subject>utter_stupidity evisceration silver.nate prediction us_politics why_oh_why_cant_we_have_a_better_press_corps why_oh_why_cant_we_have_a_better_intelligentsia via:arthegall running_dogs_of_reaction to_teach:undergrad-ADA</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:17fe7eeb33e2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:utter_stupidity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:evisceration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:silver.nate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:us_politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_press_corps"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_intelligentsia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:running_dogs_of_reaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.tnr.com/article/books-and-arts/magazine/105703/the-naked-and-the-ted-khanna">
    <title>Evgeny Morozov: The Naked And The TED | The New Republic</title>
    <dc:date>2012-08-10T15:16:26+00:00</dc:date>
    <link>http://www.tnr.com/article/books-and-arts/magazine/105703/the-naked-and-the-ted-khanna</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["I must disclose that I spoke at a TED Global Conference in Oxford in 2009, and I admit that my appearance there certainly helped to expose my argument to a much wider audience, for which I remain grateful. So I take no pleasure in declaring what has been obvious for some time: that TED is no longer a responsible curator of ideas “worth spreading.” Instead it has become something ludicrous, and a little sinister.
"Today TED is an insatiable kingpin of international meme laundering—a place where ideas, regardless of their quality, go to seek celebrity, to live in the form of videos, tweets, and now e-books. In the world of TED—or, to use their argot, in the TED “ecosystem”—books become talks, talks become memes, memes become projects, projects become talks, talks become books—and so it goes ad infinitum in the sizzling Stakhanovite cycle of memetics, until any shade of depth or nuance disappears into the virtual void. Richard Dawkins, the father of memetics, should be very proud. Perhaps he can explain how “ideas worth spreading” become “ideas no footnotes can support.” "

And, later: "Brevity may be the soul of wit, or of lingerie, but it is not the soul of analysis."]]></description>
<dc:subject>funny:malicious book_reviews cultural_criticism our_decrepit_institutions natural_history_of_truthiness natural_born_cyborgs utter_stupidity even_the_liberal_new_republic morozov.evgeny via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a6a82b1c51d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:malicious"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:book_reviews"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cultural_criticism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:our_decrepit_institutions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_history_of_truthiness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_born_cyborgs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:utter_stupidity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:even_the_liberal_new_republic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:morozov.evgeny"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://lingpipe-blog.com/2012/05/29/averages-vs-means/">
    <title>Averages vs. Means (vs. Expectations) « LingPipe Blog</title>
    <dc:date>2012-06-02T15:37:28+00:00</dc:date>
    <link>http://lingpipe-blog.com/2012/05/29/averages-vs-means/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[What a bizarre little tissue of confusions.]]></description>
<dc:subject>statistics funny:unintentionally via:arthegall</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:316d9a470129/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:unintentionally"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1203.3504">
    <title>[1203.3504] On Measurement Bias in Causal Inference</title>
    <dc:date>2012-05-10T14:26:16+00:00</dc:date>
    <link>http://arxiv.org/abs/1203.3504</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper addresses the problem of measurement errors in causal inference and highlights several algebraic and graphical methods for eliminating systematic bias induced by such errors. In particulars, the paper discusses the control of partially observable confounders in parametric and non parametric models and the computational problem of obtaining bias-free effect estimates in such models."]]></description>
<dc:subject>causal_inference inference_to_latent_objects pearl.judea to_teach:undergrad-ADA statistics via:arthegall in_NB error-in-variables</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4761849b3244/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inference_to_latent_objects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:pearl.judea"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:error-in-variables"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://httpcats.herokuapp.com/">
    <title>HTTP Status Cats</title>
    <dc:date>2011-12-16T01:28:36+00:00</dc:date>
    <link>http://httpcats.herokuapp.com/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Usage: http://httpcats.herokuapp.com/[http_status_code]"]]></description>
<dc:subject>funny:geeky lolcats web via:arsyed via:arthegall to:blog</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0465674a2dc4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:geeky"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lolcats"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arsyed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www-stat.stanford.edu/~tibs/ElemStatLearn/">
    <title>Elements of Statistical Learning: data mining, inference, and prediction. 2nd Edition.</title>
    <dc:date>2009-10-13T20:37:07+00:00</dc:date>
    <link>http://www-stat.stanford.edu/~tibs/ElemStatLearn/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Free PDF!  (Still, I find my bound physical copy much more convenient.)
]]></description>
<dc:subject>books:recommended machine_learning data_mining statistics learning_theory estimation cross-validation ensemble_methods classifiers regression graphical_models clustering dimension_reduction bootstrap via:arthegall have_read</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c0ce7a1b7506/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:recommended"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cross-validation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:classifiers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dimension_reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bootstrap"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://benfry.com/writing/archives/571">
    <title>writing | ben fry » Are electronic medical records really about data?</title>
    <dc:date>2009-10-08T01:33:54+00:00</dc:date>
    <link>http://benfry.com/writing/archives/571</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>data medicine interface_design to_teach:data-mining via:arthegall fry.ben</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:eb3f0995a090/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:medicine"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:interface_design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fry.ben"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jstor.org/stable/4175421">
    <title>Zellig Harris, &quot;Grammar on Mathematical Principles&quot; (1978)</title>
    <dc:date>2009-09-08T19:37:44+00:00</dc:date>
    <link>http://www.jstor.org/stable/4175421</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>linguistics via:arthegall to_read harris.zellig</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8f759091995f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:harris.zellig"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jstor.org/stable/20009633">
    <title>Zellig Harris, &quot;I. A Theory of Language Structure&quot; (JSTOR)</title>
    <dc:date>2009-09-08T19:37:27+00:00</dc:date>
    <link>http://www.jstor.org/stable/20009633</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>linguistics via:arthegall to_read harris.zellig</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bdb7c66ce68a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:harris.zellig"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0006777">
    <title>PLoS ONE: Parsing Social Network Survey Data from Hidden Populations Using Stochastic Context-Free Grammars</title>
    <dc:date>2009-09-07T14:23:05+00:00</dc:date>
    <link>http://www.plosone.org/article/info:doi/10.1371/journal.pone.0006777</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>network_data_analysis social_networks epidemiology statistics context-free_grammars via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:51b9de31cf67/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:epidemiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:context-free_grammars"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://homepages.cwi.nl/~lex/files/histtrpclean.pdf">
    <title>On the History of the Transportation and Maximum Flow Problems</title>
    <dc:date>2009-08-19T00:34:02+00:00</dc:date>
    <link>http://homepages.cwi.nl/~lex/files/histtrpclean.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We review two papers that are of historical interest for combinatorial optimization: an article of A.N. Tolsto˘ı from 1930, in which the transportation problem is studied, and a negative cycle criterion is developed and applied to solve a (for that time) large-scale (10 × 68) transportation problem to optimality; and an, until recently secret, RAND report of T.E. Harris and F.S. Ross from 1955, that Ford and Fulkerson mention as motivation to study the maximum ﬂow problem. The papers have in common that they both apply their methods to the Soviet railway network."  --- In a wonderful illustration of the power of duality, one of the papers was about optimizing the flow through the network, and the other was about keeping anything at all from flowing through it...
]]></description>
<dc:subject>optimization networks ussr history_of_mathematics planning cold_war via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:13b6e5b68c0f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ussr"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:history_of_mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cold_war"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0905.3369">
    <title>[0905.3369] Learning Nonlinear Dynamic Models</title>
    <dc:date>2009-06-04T00:13:53+00:00</dc:date>
    <link>http://arxiv.org/abs/0905.3369</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[... from a quick scan (the abstract is completely uninformative), this seems to be yet another near-reinvention of Knight's "prediction process".  To be read, and to act as a goad for me to finish the AoS project w/ KLK.  (I confess I am somewhat boggled at the idea that all HMMs are linear.)

Update: After a careful read, this really is just a rediscovery of predictive representations, with the trick of using regression to learn the state-transition and emission functions.  On the one hand, I feel kind of burned by seeing them calling this "entirely new" (never mind my teachers, Littman, Sutton & Singh should be very upset; so should Knight if he were still alive).  On the other hand, they got it _done_, which is a very real virtue.

Also: You need to put **** error bars on your average performance plots.  (Yes, I realize I'm nit-picking because I'm jealous.)
]]></description>
<dc:subject>prediction statistics machine_learning time_series markov_models state-space_models via:arthegall re:AoS_project langford.john zhang.tong salakhutdinov.ruslan have_read</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:27b30147e57d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:state-space_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:langford.john"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:zhang.tong"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:salakhutdinov.ruslan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.berkeley.edu/~brewer/papers/SearchDB.pdf">
    <title>Combining Systems and Databases: A Search Engine Retrospective</title>
    <dc:date>2009-05-31T14:03:10+00:00</dc:date>
    <link>http://www.cs.berkeley.edu/~brewer/papers/SearchDB.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[I won't actually teach this in 350, but I should probably mention it.
]]></description>
<dc:subject>databases information_retrieval to_teach:data-mining via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:18276d1b6a42/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.zylstra.org/blog/archives/2009/05/wolframalpha_ge.html">
    <title>Ton's Interdependent Thoughts: WolframAlpha, Getting Less Impressed Upon Closer Look</title>
    <dc:date>2009-05-05T13:16:56+00:00</dc:date>
    <link>http://www.zylstra.org/blog/archives/2009/05/wolframalpha_ge.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Nice: "For all its coolness on the front of WolframAlpha, on the back end this sounds like it's the mechanical turk of the semantic web."`
]]></description>
<dc:subject>information_retrieval wolfram_alpha via:arthegall wolfram.stephen the_mechanical_turk_of_the_semantic_web</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9eb808d4f12e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram_alpha"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram.stephen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_mechanical_turk_of_the_semantic_web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://messymatters.com/2009/03/21/the-future-is-yesterday/">
    <title>The Future is Yesterday | Messy Matters</title>
    <dc:date>2009-03-27T17:22:47+00:00</dc:date>
    <link>http://messymatters.com/2009/03/21/the-future-is-yesterday/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[If you want to predict next week's flu cases, an AR(2) model beats search-engine snooping.  Of course this relies crucially on the CDC actually generating reliable data!

(I'm curious, though, why AR(2) rather than some other autoregressive order?  Something related to the length of the infectious and incubation periods?)
]]></description>
<dc:subject>epidemiology time_series via:arthegall statistics</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:837d5420bf1c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:epidemiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nbc.com/Saturday_Night_Live/video/clips/sloths/61792/">
    <title>&quot;Saturday Night Live - Sloths!&quot;</title>
    <dc:date>2009-03-18T14:41:27+00:00</dc:date>
    <link>http://www.nbc.com/Saturday_Night_Live/video/clips/sloths/61792/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[I'm really not sure I needed that...
]]></description>
<dc:subject>sloths funny:tasteless via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f3ce4a8daf26/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sloths"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:tasteless"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://norvig.com/fact-check.html">
    <title>All we want are the facts, ma'am</title>
    <dc:date>2009-02-24T12:58:43+00:00</dc:date>
    <link>http://norvig.com/fact-check.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[When I wrote about Chris Anderson's idiotic piece back in the spring, I didn't say anything about the quote from Norvig, because it sounded very strange and not at all like Norvig.  And, indeed, he now says "That's a silly statement, I didn't say it, and I disagree with it."  Ah, Wired!
]]></description>
<dc:subject>why_oh_why_cant_we_have_a_better_press_corps anderson.chris statistics modeling data_mining norvig.peter machine_learning bad_science_journalism fact_checking via:arthegall via:shivak</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4e2b6310e4fc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_press_corps"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:anderson.chris"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:norvig.peter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bad_science_journalism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fact_checking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:shivak"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://differ.raysend.com/sex-differences-in-iq-variabil-0">
    <title>Sex differences in IQ variability - The differential biology reader</title>
    <dc:date>2009-02-24T00:09:37+00:00</dc:date>
    <link>http://differ.raysend.com/sex-differences-in-iq-variabil-0</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Figures from the Johnson/Carothers/Deary paper, for ease of reference.
]]></description>
<dc:subject>iq sex_differences re:g_paper via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:47d7403583da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:iq"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sex_differences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:g_paper"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.1533">
    <title>Stacked generalization</title>
    <dc:date>2009-02-18T21:55:25+00:00</dc:date>
    <link>http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.56.1533</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[I read this a long time ago, and then forgot about it (except for vague comments to students).
]]></description>
<dc:subject>ensemble_methods machine_learning via:arthegall to_teach:data-mining wolpert.david</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bf99d4287ea7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ensemble_methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolpert.david"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cog.brown.edu/~mj/papers/JohnsonGriffithsGoldwater06AdaptorGrammars.pdf">
    <title>Adaptor Grammars: A Framework for Specifying Compositional Nonparametric Bayesian Models (Johnson, Griffiths and Goldwater)</title>
    <dc:date>2009-02-06T18:26:51+00:00</dc:date>
    <link>http://www.cog.brown.edu/~mj/papers/JohnsonGriffithsGoldwater06AdaptorGrammars.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["introduces adaptor grammars, a class of probabilistic models of language that generalize probabilistic context-free grammars (PCFGs). ... ars augment the ... rules of PCFGs with “adaptors” that can induce dependencies among successive uses. With a particular choice of adaptor, based on the Pitman-Yor process, nonparametric Bayesian models of language using Dirichlet processes and hierarchical Dirichlet processes can be written as simple grammars. We present a general-purpose inference algorithm for adaptor grammars, making it easy to deﬁne and use such models, and illustrate how several existing nonparametric Bayesian models can be expressed within this framework."  --- Looking at posterior or predictive consistency here would I think be interesting, but hard.
]]></description>
<dc:subject>grammar_induction statistics context-free_grammars nonparametrics machine_learning via:arthegall statistical_inference_for_stochastic_processes</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1a433aa265b6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:grammar_induction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:context-free_grammars"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://pipeline.corante.com/archives/2009/01/19/ten_years_after_the_genomics_frenzy.php">
    <title>Ten Years After: The Genomics Frenzy. In the Pipeline:</title>
    <dc:date>2009-02-06T17:30:17+00:00</dc:date>
    <link>http://pipeline.corante.com/archives/2009/01/19/ten_years_after_the_genomics_frenzy.php</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>genomics market_bubbles via:arthegall intellectual_property</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5ef79dde7fa5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genomics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:market_bubbles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:intellectual_property"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.uwaterloo.ca/~mackerma/ClusteringQualityPaper.pdf">
    <title>Margaret Ackerman and Shai Ben-David, &quot;Measures of Clustering Quality: A Working Set of Axioms for Clustering&quot;</title>
    <dc:date>2008-12-13T19:59:25+00:00</dc:date>
    <link>http://www.cs.uwaterloo.ca/~mackerma/ClusteringQualityPaper.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[A rebuttal to Kleinberg's impossibility theory for clustering (bookmarked earlier).  There are measures of _cluster quality_ which satisfy all the natural axioms, which is good enough.
]]></description>
<dc:subject>clustering to_teach:data-mining via:arthegall via:vielmetti data_mining ackerman.margaret ben-david.shai kleinberg.jon</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cd7b13d7fdb5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:vielmetti"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ackerman.margaret"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ben-david.shai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kleinberg.jon"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://radfordneal.wordpress.com/">
    <title>Radford Neal's blog</title>
    <dc:date>2008-08-19T14:14:13+00:00</dc:date>
    <link>http://radfordneal.wordpress.com/</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>blogs statistics machine_learning via:arthegall neal.radford</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3c4e51abf0f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:blogs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neal.radford"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.powells.com/review/2008_08_14.html">
    <title>Beyond the Hoax: Science, Philosophy and Culture by Alan Sokal, reviewed by Simon Blackburn</title>
    <dc:date>2008-08-18T14:52:18+00:00</dc:date>
    <link>http://www.powells.com/review/2008_08_14.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Query to self: does this sort of deflation of the claim "science gives us the truth" (by using Tarski to turn that into the OR of lots of claims like "science says that the earth circles the sun, and it does") still work counterfactually?  That is, if the Sun _did_ go around the Earth, presumably scientists could figure that out...  (Cf. Kevin Kelly, _Logic of Reliable Inquiry_.)
]]></description>
<dc:subject>book_reviews blackburn.simon the_french_disease philosophy_of_science epistemology via:arthegall truth sokal.alan</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0dfeb35aac2b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:book_reviews"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:blackburn.simon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_french_disease"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:philosophy_of_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:epistemology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:truth"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sokal.alan"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.qwantz.com/archive/000767.html">
    <title>Occam's Razor - qwantz.com - dinosaur comics - May 03 2006</title>
    <dc:date>2008-08-04T21:38:05+00:00</dc:date>
    <link>http://www.qwantz.com/archive/000767.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Must show this to Kevin.
]]></description>
<dc:subject>occams_razor dinosaur_comics via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:03703082e087/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:occams_razor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dinosaur_comics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nature.com/ng/journal/v40/n5/abs/ng.139.html">
    <title>Novembre and Stephens, &quot;Interpreting principal component analyses of spatial population genetic variation&quot; (Nature Genetics)</title>
    <dc:date>2008-05-13T19:38:16+00:00</dc:date>
    <link>http://www.nature.com/ng/journal/v40/n5/abs/ng.139.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We find that gradients and waves observed in ... maps resemble sinusoidal mathematical artifacts that arise generally when PCA is applied to spatial data, implying that the patterns do not necessarily reflect specific migration events."
]]></description>
<dc:subject>genetics human_genetics statistics principal_components spatial_statistics stepping_stone_model via:arthegall bad_data_analysis to_teach:data-mining to_teach:undergrad-ADA in_NB cavalli-sforza.l.luca</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0959af5a1b2b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:human_genetics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:principal_components"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spatial_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stepping_stone_model"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bad_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cavalli-sforza.l.luca"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://xkcd.com/231/">
    <title>&quot;Cat Proximity&quot; (xkcd)</title>
    <dc:date>2008-05-13T14:49:23+00:00</dc:date>
    <link>http://xkcd.com/231/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Classic (& thanks for the reminder).  An accurate depiction of my domestic life.
]]></description>
<dc:subject>cats comics funny:malicious via:arthegall story_of_my_life xkcd</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:673f92bf65ee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cats"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:comics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:malicious"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:story_of_my_life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:xkcd"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.slate.com/id/2081746/">
    <title>&quot;Unforeseeables&quot;</title>
    <dc:date>2008-05-03T13:38:06+00:00</dc:date>
    <link>http://www.slate.com/id/2081746/</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>poetry via:arthegall unintended_consequences the_nightmare_from_which_we_are_trying_to_awake goldbarth.arthur</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:04eba88f68c1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:poetry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:unintended_consequences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_nightmare_from_which_we_are_trying_to_awake"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goldbarth.arthur"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.lecun.org/gallery/libpro/20011121-allyourbayes/index.html">
    <title>Vapnik: ALL YOUR BAYES ARE BELONG TO US</title>
    <dc:date>2008-04-09T11:11:19+00:00</dc:date>
    <link>http://www.lecun.org/gallery/libpro/20011121-allyourbayes/index.html</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>funny:geeky via:arthegall photos vapnik.vladimir machine_learning learning_theory blogged</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b1f771e437e8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:geeky"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:photos"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:vapnik.vladimir"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:blogged"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.efalken.com/papers/VaR.PDF">
    <title>Value-at-Risk and Derivatives Risk</title>
    <dc:date>2008-03-29T18:54:55+00:00</dc:date>
    <link>http://www.efalken.com/papers/VaR.PDF</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>finance risk_vs_uncertainty via:arthegall falkenstein.eric risk_assessment</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0e673461bac9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:finance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:risk_vs_uncertainty"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:falkenstein.eric"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:risk_assessment"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.stat.columbia.edu/~gelman/research/unpublished/multiple2.pdf">
    <title>Why we (usually) don’t have to worry about multiple comparisons</title>
    <dc:date>2008-03-21T18:09:17+00:00</dc:date>
    <link>http://www.stat.columbia.edu/~gelman/research/unpublished/multiple2.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[My initial reaction is one of skepticism, despite my respect for Andy.  To work through.
]]></description>
<dc:subject>statistics multiple_comparisons gelman.andrew via:arthegall have_read hill.jennifer hierarchical_statistical_models</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9788bd7d3ebb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:multiple_comparisons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gelman.andrew"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hill.jennifer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hierarchical_statistical_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://econpapers.repec.org/paper/nbrnberwo/12632.htm">
    <title>EconPapers: Does Television Cause Autism?</title>
    <dc:date>2008-03-06T21:04:42+00:00</dc:date>
    <link>http://econpapers.repec.org/paper/nbrnberwo/12632.htm</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[This is a joke, right?  Right?  Somebody please tell me this is a joke...

ETA: It's not a joke.  It's now a negative example in ADA.

Ungated version: http://forum.johnson.cornell.edu/faculty/waldman/autism-waldman-nicholson-adilov.pdf]]></description>
<dc:subject>please_give_me_strength autism econometrics statistics linear_regression television via:arthegall causal_inference instrumental_variables to_teach:undergrad-ADA</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3ff5ffd508da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:please_give_me_strength"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:autism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:econometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linear_regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:television"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:causal_inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:instrumental_variables"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.tnr.com/story_print.html?id=d6977c2f-4788-468e-8f63-2e92109320fe">
    <title>Jackboots and Whole Foods</title>
    <dc:date>2008-02-27T03:54:54+00:00</dc:date>
    <link>http://www.tnr.com/story_print.html?id=d6977c2f-4788-468e-8f63-2e92109320fe</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[... in which Michael Tomasky's time is wasted reading and reviewing garbage.  Perhaps this was the point?
]]></description>
<dc:subject>book_reviews evisceration goldberg.jonah liberalism fascism utter_stupidity via:arthegall tomasky.michael</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:54ec97b2973c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:book_reviews"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:evisceration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:goldberg.jonah"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:liberalism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fascism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:utter_stupidity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tomasky.michael"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://dbpubs.stanford.edu/~klein/lagrange-multipliers.pdf">
    <title>Lagrange Multipliers without Permanent Scarring (Dan Klein)</title>
    <dc:date>2008-01-18T17:24:04+00:00</dc:date>
    <link>http://dbpubs.stanford.edu/~klein/lagrange-multipliers.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Nicely done.
]]></description>
<dc:subject>to_teach tutorials optimization via:arthegall to_teach:data-mining to_teach:complexity-and-inference to_teach:undergrad-ADA to_teach:statcomp mathematics re:freshman_seminar_on_optimization</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5bff31a6647a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tutorials"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:complexity-and-inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statcomp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:freshman_seminar_on_optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0711.0194">
    <title>[0711.0194] Coinductive Proof Principles for Stochastic Processes</title>
    <dc:date>2007-11-30T18:08:51+00:00</dc:date>
    <link>http://arxiv.org/abs/0711.0194</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>stochastic_processes mathematical_logic via:arthegall in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:35889aef7a86/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mathematical_logic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://cg.scs.carleton.ca/~luc/rnbookindex.html">
    <title>Non-Uniform Random Variate Generation</title>
    <dc:date>2007-11-12T16:09:11+00:00</dc:date>
    <link>http://cg.scs.carleton.ca/~luc/rnbookindex.html</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>computational_statistics devroye.luc via:arthegall why_oh_why_cant_we_have_a_better_academic_publishing_system books:noted in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2937ed191d0a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:devroye.luc"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_academic_publishing_system"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:noted"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>