Math and Statistics Geeks
http://www.dailykos.com/user/Math and Statistics Geeks/rss/index.xml
For questions, answers, thoughts and stuff about math and statistics. Also for sharing of data sets, requests for analysis, debunking statistics cited by RWNJ, and so on.
Copyright 2005 - Steal what you wantTue, 02 Jun 2015 14:45:14 UTCTue, 02 Jun 2015 14:45:14 UTCDaily Kos rss@dailykos.com (Daily Kos)Daily Kos rss@dailykos.com (Daily Kos)Five simple line charts re: Stephen Wolf's epic first Appalachian diary
http://www.dailykos.com/story/2013/12/06/1260675/-Five-simple-line-charts-re-Stephen-Wolf-s-epic-first-Appalachian-diary
<p>Stephen Wolf published an <a href="http://www.dailykos.com/story/2013/11/19/1255733/-Political-Geography-What-if-Appalachia-Were-its-Own-State">awe-inspiring, comprehensive diary</a> here last month about what an Appalachian state would look like, demographically and politically speaking.</p>
<p>Substantively, I have nothing to add. But when I was reading the diary, at times I wished there were some simple line charts as well as all the awesome maps, so I could get a somewhat clearer grasp of the overall trends involved. So I made a couple myself. Might as well share them here - see below the fold.</p>
rss@dailykos.com (nimh)AppalachiaDemocratsDemographicsDK ElectionsElectionsHistoryPopulationPresidential ElectionsStephen Wolf_1260675Fri, 06 Dec 2013 18:57:21 UTCMath and statistics geeks: Rebirth
http://www.dailykos.com/story/2013/11/18/1256410/-Math-and-statistics-geeks-Rebirth
<p>A while back I started the group "Math and Statistics Geeks". It was active for some time, but hasn't been in about a year and a half.</p>
<p>Then, over the weekend, I noticed <strong>Andrew Lazarus</strong>'s excellent diary <a href="http://www.dailykos.com/story/2013/11/16/1256019/-Vaccinate-yourself-against-statistical-idiocy">vaccinate yourself against statistical idiocy</a> on the rec list and that gave me the motivation to re-start the group.</p>
<p>Math is a part of being human. It is dreadfully mistaught and misunderstood.</p>
<p>Statistics are vital to understanding all sorts of issues; of particular relevance here are polls, but statistical thinking is involved in climate change, health care, policy review, education reform and many other topics.</p>
<p>I am a statistician for a living and I think it's vital to have an educated electorate. I can't manage that on my own, but at least I can take a shot at an educated bunch of Kossacks. :-)</p>
<p>If you're interested in joining, let me know. If you see diaries that should be republished as part of this group, let me know. If you have questions, let me know.</p>
<p>And I hope we can get the group active again.</p>
rss@dailykos.com (plf515)MathMetaStatistics_1256410Mon, 18 Nov 2013 13:50:09 UTCConservative Statistical Fraud, Forbes 9/23 edition
http://www.dailykos.com/story/2013/09/24/1240906/-Conservative-Statistical-Fraud-Forbes-9-23-edition
<p>The most popular story on the Forbes.com website at this moment (Monday afternoon) is headlined “<a href="http://www.forbes.com/sites/theapothecary/2013/09/23/its-official-obamacare-will-increase-health-spending-by-7450-for-a-typical-family-of-four/">Obamacare Will Increase Health Spending By $7,450 For A Typical Family of Four</a>”. Wow! That sounds bad! Until we see how this nonsense-number got calculated (under the fold)!</p>
rss@dailykos.com (Andrew Lazarus)Affordable Care ActForbesHealth CareRecommendedRescuedRescued to RecommendedStatistics_1240906Tue, 24 Sep 2013 01:22:35 UTCVaccinate yourself against statistical idiocy
http://www.dailykos.com/story/2013/11/17/1256019/-Vaccinate-yourself-against-statistical-idiocy
<p>This week’s hot Internet story was <a href="http://www.newrepublic.com/article/115551/jenny-mccarthy-anti-vaccination-movement-blame-whooping-cough">Julia Ioffe writing</a> in The New Republic about her whooping cough. [Mention on <a href="http://www.dailykos.com/story/2013/11/11/1254857/-Open-thread-for-night-owls-Thanks-a-lot-Jenny-McCarthy">DK FP</a>; <a href="http://www.volokh.com/2013/11/12/julia-joffe-jenny-mccarthy/">Volokh Conspiracy</a>; <a href="http://blogs.discovermagazine.com/gnxp/2013/11/vaccination-social-information-networks/#.UocGD5Q4VHA">Discover</a>] As she points out, whooping cough (also known as <a href="http://en.wikipedia.org/wiki/Pertussis">pertussis</a>) had almost disappeared in the United States, but <a href="http://www.npr.org/blogs/health/2013/09/25/226147147/vaccine-refusals-fueled-californias-whooping-cough-epidemic">cases are on the rise</a>. One reason is that a growing number of Americans are refusing to vaccinate their children.</p>
<p>As expected by anyone who has ever seen vaccination discussed on the Internet, Ioffe’s comments section rapidly filled with anti-vaccine cranks. Some approach from the right, with claims of personal autonomy that trump even the libertarian night-watchman state's power of quarantine. Others come from a narcissistic pseudo-Green belief that their Superman immune systems, fortified with expensive supplements, can take on all those pesky germs. How dare we ordinary people complain that in reality they are <a href="http://en.wikipedia.org/wiki/Free_rider_problem">free-riding</a> on our assuming the non-zero (albeit small) risks of vaccination! [Note: autism is <em>not</em> one of these risks.]</p>
<p>Either way the denialists have a major statistical problem: the near-eradication of several diseases in the course of vaccination campaigns. Flailing attempts to solve this problem include: Big Pharma has persuaded doctors to reclassify paralytic polio as something else; sanitation and hygiene improved; the disease rates were going down before vaccines; and people who are vaccinated still get sick (no one, of course, denied this).</p>
<p>No pseudo-scientific campaign is complete without pseudo-statistical nonsense, and in following the antivax links I encountered some real doozies. A few of them are generalizable to bad statistical reasoning in general, so for the details and maybe a good laugh, follow below the cronut.</p>
rss@dailykos.com (Andrew Lazarus)Anti-VaccinationdiphtheriaJulia IoffeMarin CountymeningitisPertussisPolioPoliomyelitisRecommendedstatistical fraudStatisticsThe New RepublicVaccination_1256019Sun, 17 Nov 2013 01:43:45 UTCMad (Statistics) Men vs. the Bigots. What a Difference a Year Makes.
http://www.dailykos.com/story/2012/06/05/1096802/-Mad-Statistics-Men-vs-the-Bigots-What-a-Difference-a-Year-Makes
<p>I woke up yesterday morning and decided to do something nerdy. (Doesn't everyone?)</p>
<p>Thanks to Nate Silver's famous graphics, we know that national polling for marriage equality has been rising at about 2% per year since 2004, and opposition has been falling at the same rate, for a net gain of 4% per annum and reaching 50% support for same-sex marriage this year. But what about state polling data, where the people who are polled are generally registered voters, not all adults as are asked by most of the national polls?</p>
<center><br />
<a href="http://s552.photobucket.com/albums/jj321/jpmassar/?action=view&current=nate-silver-marriage-equality-2012.jpg" target="_blank"><img src="http://i552.photobucket.com/albums/jj321/jpmassar/nate-silver-marriage-equality-2012.jpg" border="0" alt="Photobucket" /></a><br />
<small>"Americans will never accept the legitimacy of gay marriage"<br />
<a href="http://www.lgbtqnation.com/2012/06/perkins-americans-will-never-accept-gay-marriage-because-it-violates-reason-natural-law/">Family Research Council President Tony Perkins</a><br /></small><br /></center>
<p>I decided to look at the most recent 2012 polling for marriage equality in each state that had such polling, and then compare it to polling done as close to a year ago in that state on the same topic -- again, if such polling existed.</p>
<p>It turns out that (thanks mostly to <i>Public Policy Polling</i>) there are seventeen states with such polling data. Here's the upshot.</p>
<center>
<h2><b>Between 2011 and 2012, the average swing in state polling of registered voters on marriage equality has been 6.3%, compared to the 4% national swing for adults.</b></h2>
</center>
<br />
rss@dailykos.com (jpmassar)Civil RightsEqual RightsLGBTlies damned lies and statisticsMarriage EqualityPollsSame-Sex MarriageStatistics_1096802Tue, 05 Jun 2012 02:32:17 UTCNumber Sense 046
http://www.dailykos.com/story/2012/03/24/1077387/-Number-Sense-046
<p>Last week, in <a href="http://www.dailykos.com/story/2012/03/17/1075211/-Number-Sense-045?showAll=yes">Number Sense 045</a>, Awkward Goat and Billy Goat Gruff found that their new Butts operation was associative, and, since Butts had an identity element, inverses and was closed, it formed a group. </p>
<p>This week they decided to explore operations a bit more, and made up another one.</p>
rss@dailykos.com (Orinoco)abstract algebraassociative propertyMathMathematicsTeaching_1077387Sat, 24 Mar 2012 16:28:54 UTCNumber Sense 045
http://www.dailykos.com/story/2012/03/17/1075211/-Number-Sense-045
<p>Last week, in <a href="http://www.dailykos.com/story/2012/03/10/1073108/-Number-Sense-044?showAll=yes">Number Sense 044</a>, Awkward Goat and Billy Goat Gruff invented a new operation, called Butts, which worked with three colors, Red, Yellow and Green. Butts has an identity element, Yellow, and is commutative. The jury is still out on whether Butts is associative or not.</p>
rss@dailykos.com (Orinoco)abstract algebraassociativegroupMathMathematicsTeaching_1075211Sat, 17 Mar 2012 18:23:39 UTCNumber Sense 044
http://www.dailykos.com/story/2012/03/10/1073108/-Number-Sense-044
<p>Last week, in <a href="http://www.dailykos.com/story/2012/03/03/1070549/-Number-Sense-043?showAll=yes&via=blog_665347">Number Sense 043</a>, Awkward Goat and Billy Goat Gruff thought they proved that clock arithmetic was commutative and associative. But there is trouble in paradise...</p>
rss@dailykos.com (Orinoco)abstract mathassociativebegging the questioncommutativeMathMathematics_1073108Sat, 10 Mar 2012 18:31:00 UTCNumber Sense 043
http://www.dailykos.com/story/2012/03/03/1070549/-Number-Sense-043
<p>Last week, in <a href="http://www.dailykos.com/story/2012/02/25/1068241/-Number-Sense-042?showAll=yes&via=blog_665347">Number Sense 042</a>, Awkward Goat and Billy Goat Gruff discovered that clock arithmetic was closed under addition, all sums were included in the original set of numbers. So far, clock addition has proved to have closure and an identity element in common with ordinary addition. Our intrepid Capra aegagrus hirci continue their search for more common properties.</p>
rss@dailykos.com (Orinoco)associativeclock arithmeticcommutativeMathMathematicsmodular arithmetic_1070549Sat, 03 Mar 2012 15:35:45 UTCNumber Sense 042
http://www.dailykos.com/story/2012/02/25/1068241/-Number-Sense-042
<p>Last week, in <a href="http://www.dailykos.com/story/2012/02/18/1066115/-Number-Sense-041?showAll=yes&via=blog_665347">Number Sense 041</a>, Awkward Goat and Billy Goat Gruff found that clock arithmetic has an identity element for addition: zero. This week they keep looking for more properties in common with ordinary arithmetic.</p>
rss@dailykos.com (Orinoco)closureMathMathematicsmodular arithmeticset theory_1068241Sat, 25 Feb 2012 18:43:15 UTCNumber Sense 041
http://www.dailykos.com/story/2012/02/18/1066115/-Number-Sense-041
<p>Last week, in <a href="http://www.dailykos.com/story/2012/02/11/1063876/-Number-Sense-040">Number Sense 040</a>, Awkward Goat and Billy Goat Gruff discovered they had invented a clock, by walking around a tree. At least, they discovered a facet of clock arithmetic. Billy Goat Gruff, however, suspected he'd been snookered, somehow, so this week finds them back at the same tree.</p>
rss@dailykos.com (Orinoco)clock arithmeticidentity elementMathMathematicsmodular arithmeticRescuedTeaching_1066115Sat, 18 Feb 2012 14:54:00 UTCNumber Sense 040
http://www.dailykos.com/story/2012/02/11/1063876/-Number-Sense-040
<p>Last week, in <a href="http://www.dailykos.com/story/2012/02/04/1061770/-Number-Sense-039?showAll=yes&via=blog_665347">Number Sense 039</a>, Awkward Goat and Billy Goat Gruff explored Fibonacci series using Leonardo of Pisa's classic rabbit reproduction puzzle. They decided sauce for the goose wouldn't really work for the gander, besides, metaphors involving cooking farm animals left them feeling a bit queasy.</p>
<p>This week finds them wandering in a circle around a tree...</p>
rss@dailykos.com (Orinoco)clock arithmeticMathMathematicsmodular arithmeticTeaching_1063876Sat, 11 Feb 2012 18:37:32 UTCNumber Sense 039
http://www.dailykos.com/story/2012/02/04/1061770/-Number-Sense-039
<p>Last week, in <a href="http://www.dailykos.com/story/2012/01/28/1057871/-Number-Sense-038?showAll=yes&via=blog_665347">Number Sense 038</a>, Awkward Goat proved that a complete list of prime numbers could not be made, because there was no end to prime numbers: more could always be found and added to any supposed complete list of prime numbers. He didn't phrase it quite this way, but he proved there are an infinite number of primes. This week, the weather is unseasonably warm, daffodils are poking their buds above the ground, and spring is in the air.</p>
rss@dailykos.com (Orinoco)fibonacci seriesGoatsMathMathematicsRescuedTeaching_1061770Sat, 04 Feb 2012 18:18:44 UTCNumber Sense 038
http://www.dailykos.com/story/2012/01/28/1057871/-Number-Sense-038
<p>Last week, in <a href="http://www.dailykos.com/story/2012/01/21/1056920/-Number-Sense-037?showAll=yes&via=blog_665347">Number Sense 037</a>, Awkward Goat proved that all counting numbers (numbers of goats in formation for the Marching Goat Society) were either prime numbers or the product of prime numbers (although he called them primary numbers, analogous to primary colors) much to Billy Goat Gruff's dismay. This week, the goats got together to discuss these awkward numbers a bit more</p>
rss@dailykos.com (Orinoco)MathMathematicsPrime NumbersproofRescuedTeaching_1057871Sat, 28 Jan 2012 15:47:39 UTCNumber Sense 037
http://www.dailykos.com/story/2012/01/21/1056920/-Number-Sense-037
<p>Last week, in <a href="http://www.dailykos.com/story/2012/01/14/1054757/-Number-Sense-036?showAll=yes&via=blog_665347">Number Sense 036</a>, Awkward Goat challenged the Marching Goat Society to disprove his conjecture that every time they got into formation, their rows and their columns were awkward numbers, or the product of awkward numbers. The Marching Goats couldn't do it with only ten goats, but they vowed to return this week, with many more goats, to prove Awkward Goat wrong.</p>
rss@dailykos.com (Orinoco)fundamental theorem of arithmetic MathMathematicsproofRescuedTeaching_1056920Sat, 21 Jan 2012 15:15:10 UTCSome thoughts on observational studies
http://www.dailykos.com/story/2012/01/20/1056640/-Some-thoughts-on-observational-studies
<p>In statistics and research design, there are two types of study: Experiments and observational studies. Some people also use the term "quasi-experiment" but I do not like it. In an experiment, the key thing is <em>randomization</em>. We assign subjects (e.g. people) to different conditions (e.g. drug and placebo) randomly. Often, though, such assignment is not possible or not ethical. In social sciences, it is rarely possible. We cannot, for example, randomly assign people to different levels of education. We can only observe relationships between (say) education and political party.</p>
<p>When we present social science research, we often get the "correlation is not causation" reply. Indeed, these two are not equivalent. More correctly "correlation does not imply causation" - that is, two things can be related without one causing another. Sometimes, though, this is taken too far. While correlation does not <em>imply</em> causation, it is <em>evidence</em> of causation. And we can strengthen that evidence. There are at least three ways this can be done:</p>
<p>1) Control for other variables that might be relevant<br />
2) Show a large effect size, even after the control<br />
3) Show the mechanism that makes the relationship work.</p>
<p>Let's take each in turn:<br />
1) Control for other variables. This means to take them into account. There are various ways to do this in statistics, but most commonly we add them to some form of regression equation. A negative example: The more firefighters show up at a fire, the more damage is done. This does NOT imply that firefighters cause damage, and if we control for size of fire, the relationship inverts. A positive example: Smoking is related to lung cancer (and many other ills). This relationship exists even if we control for age, ethnicity, sex, weight, diet, exercise and many other variables. This increases the evidence that smoking causes cancer.</p>
<p>2) Show a large effect size even after controlling for other variables. Large effect sizes are hard to explain by other causes. This doesn't mean impossible, it just means that one of the variables we haven't controlled for must have a strong relationship to the variable we are studying. In the case of smoking, this was eminently true. Smokers have much higher rates of cancer, even after accounting for all those other factors. Could something else be accounting for this relationship? Yes. But it's hard to imagine what it could be.</p>
<p>3) Show the mechanism that makes the relationship work. Relationships that are unexplained are more suspect that those that are explained. Of course, our explanation could be wrong, but a good explanation is an additional bit of evidence that the relationship is real.</p>
rss@dailykos.com (plf515)observational studiesStatisticsStudies_1056640Fri, 20 Jan 2012 19:52:44 UTCNumber Sense 036
http://www.dailykos.com/story/2012/01/14/1054757/-Number-Sense-036
<p>Last week, in <a href="http://www.dailykos.com/story/2012/01/07/1052447/-Number-Sense-035?showAll=yes&via=blog_665347">Number Sense 035</a>, we took a look at a proof for the formula we developed for adding up series of numbers. I really wasn't happy with the way it turned out, so we are going to shift gears a bit, and bring back the goats.</p>
<p>The goats joined a close order drill society and learned how to march in formation.</p>
rss@dailykos.com (Orinoco)GoatsMathMathematicsPrime NumbersRescuedTeaching_1054757Sat, 14 Jan 2012 20:38:18 UTCNumber Sense 035
http://www.dailykos.com/story/2012/01/07/1052447/-Number-Sense-035
<p>Last week, in <a href="http://www.dailykos.com/story/2011/12/31/1050259/-Number-Sense-034?detail=hide&via=blog_665347">Number Sense 034</a>, we developed a formula for figuring out the sum of a series of numbers. We tried out our formula on a couple of examples, and it worked. We also came up with a diagram showing how the formula found the sum for one of the examples. But we didn't prove the formula was true. Two or three examples of it working does not prove it will always work. In order to do that, we must be a bit more rigorous.</p>
rss@dailykos.com (Orinoco)algebradeductionInductionMathMathematicsproof_1052447Sat, 07 Jan 2012 17:08:07 UTCNumber Sense 034
http://www.dailykos.com/story/2011/12/31/1050259/-Number-Sense-034
<p>Last week in <a href="http://www.dailykos.com/story/2011/12/24/1048525/-Number-Sense-33?showAll=yes&via=blog_665347">Number Sense 033</a>, we took a look at an equation that produced a parabola when it was plotted on Cartesian coordinates. This opens up the possibility of a situation having two solutions, or no solutions. This week I'd like to change course a bit, and begin a discussion about how we know mathematical things.</p>
rss@dailykos.com (Orinoco)MathMathematicsnumber seriesproofRescuedTeaching_1050259Sat, 31 Dec 2011 17:12:20 UTCNumber Sense 33
http://www.dailykos.com/story/2011/12/24/1048525/-Number-Sense-33
<p>Last week, in Number Sense 32, we took two linear equations and plotted them on a graph, and discovered that the intersection of the two lines gave us a solution that worked for both equations. This is a very powerful idea.</p>
<p>Neither of the linear equations had a single solution. We could pick many different values for the amount of liquid milk, and then use one of the linear equations to calculate how much we had left to make cheese, and still not know how much was actually used.</p>
<p>If we used the other equation, again, we could pick many different values for the amount of liquid milk, and calculate the amount of milk used for cheese, and still not know how much was actually used.</p>
<p>But! when we combined those two equations, there was only one combination of liquid milk and cheese milk that worked for both. There was AN ANSWER! A single, gotta be this, honest to god answer, just like the answers we got in arithmetic when we were asked to add 3 plus 6.</p>
rss@dailykos.com (Orinoco)graphMathMathematicsparabolaRescuedTeaching_1048525Sat, 24 Dec 2011 17:30:53 UTCNumber Sense 32
http://www.dailykos.com/story/2011/12/17/1046364/-Number-Sense-32
<p>Last week, in <a href="http://www.dailykos.com/story/2011/12/10/1043953/-Number-Sense-031?showAll=yes&via=blog_665347">Number Sense 31</a>, we made a graph of a more continuous function: how much grass a herd of goats might eat each hour. We also took a look at what the graph might look like if it were an inequality, rather than a strict equality. This week we are going to solve a problem using a graph.</p>
rss@dailykos.com (Orinoco)graphMathMathematicsRescuedsolving systems of equalitiesTeaching_1046364Sat, 17 Dec 2011 16:37:41 UTCNumber Sense 031
http://www.dailykos.com/story/2011/12/10/1043953/-Number-Sense-031
<p>Last week, in <a href="http://www.dailykos.com/story/2011/12/03/1042054/-Number-Sense-030?detail=hide&via=blog_665347">Number Sense 030</a>, we took a look at a situation where two quantities were related to each other. We used Cartesian coordinates, commonly called a graph. This week I'm going to expand on the graph a bit, and take a look at what else we can do with it.</p>
rss@dailykos.com (Orinoco)graphInequalityMathMathematicsRescuedTeaching_1043953Sat, 10 Dec 2011 16:47:22 UTCNumber Sense 030
http://www.dailykos.com/story/2011/12/03/1042054/-Number-Sense-030
<p>Last week, in <a href="http://www.dailykos.com/story/2011/11/26/1040048/-Number-Sense-029?showAll=yes&via=blog_665347">Number Sense 029</a> we added and subtracted nothing from our equations, and found that to be a useful technique.</p>
<p>Up until now, we have been dealing with one unknown, one goat, and we have come up with methods for finding the value of that goat. But what do we do when we have more than one unknown?</p>
<p>Real problems are considerably messier than the simple problems we set up to teach basic ideas, simple problems are rarely encountered in the real world, or, when they are, can be solved with the most simple mechanical methods.</p>
<p>Have you ever played cards? When you dealt the cards, did you think your were dividing a certain number of cards by the number of players? Probably not. You just dealt the cards, one at a time, to each player in turn. A simple real world mathematical problem, solved so simply that few people even think they are doing math when they solve that problem.</p>
<p>This week we will begin to look at problems where there are two unknown quantities, somehow related to each other.</p>
rss@dailykos.com (Orinoco)cartesian coordinatesgraphsMathMathematicsRescuedTeaching_1042054Sat, 03 Dec 2011 20:44:45 UTCNumber Sense 029
http://www.dailykos.com/story/2011/11/26/1040048/-Number-Sense-029
<p>Last week, in <a href="http://www.dailykos.com/story/2011/11/19/1038103/-Number-Sense-028?showAll=yes&via=blog_665347">Number Sense 028</a> we put some goats on a scale to solve an algebra problem. This week, we are going to play tricks on the scale, by adding and subtracting nothing.</p>
rss@dailykos.com (Orinoco)algebraequationsMathMathematicsoppositesTeaching_1040048Sat, 26 Nov 2011 16:20:45 UTCNumber Sense 028
http://www.dailykos.com/story/2011/11/19/1038103/-Number-Sense-028
<p>Last week, in <a href="http://www.dailykos.com/story/2011/11/12/1035745/-Number-Sense-027?showAll=yes&via=blog_665347">Number sense 027</a>, we outlined the rules of the algebra game.</p>
<p>It was some pretty rough sledding, and there weren't any goats around to liven things up. This week, I'm going to see how we can use these algebra properties and to solve some problems<br /></p>
rss@dailykos.com (Orinoco)balanceequationsMathMathematicsTeaching_1038103Sat, 19 Nov 2011 18:40:27 UTCNumber Sense 027
http://www.dailykos.com/story/2011/11/12/1035745/-Number-Sense-027
<p>Last week, in <a href="http://www.dailykos.com/story/2011/11/05/1033404/-Number-Sense-026?showAll=yes&via=blog_665347">Number sense 026</a>, we took a look at equality, the equal sign in mathematics, meaning nothing more or less than a statement that one thing is the same as another thing. In arithmetic, the equal sign often gets an operational definition of: do a calculation and put results here. This operational definition often interferes with learning algebra, because algebra is not really about calculating, but about exploring and discovering.</p>
<p>Algebra is a game, and, like most games, there are rules, and moves that are allowed, and moves that are not allowed. Games have goals, a way to win, so does algebra.</p>
<p>This week, I'm going to outline the rules of the game.</p>
rss@dailykos.com (Orinoco)algebraMathMathematicsPrinciplesRescuedRulesTeaching_1035745Sat, 12 Nov 2011 21:01:11 UTCNumber Sense 026
http://www.dailykos.com/story/2011/11/05/1033404/-Number-Sense-026
<p>Last week, in <a href="http://www.dailykos.com/story/2011/10/29/1031116/-Number-Sense-025?detail=hide&via=blog_665347">Number Sense 025</a>, we took up that classic word problem of two trains passing in the night. Upon reflection, jumping so far ahead was a mistake. So I'm going to pretend it was just a one-of-a-kind lump in the pudding, and continue on from <a href="http://www.dailykos.com/story/2011/10/22/1028947/-Number-Sense-024?showAll=yes&via=blog_665347">Number Sense 24</a>, where we completed a model of an addition problem, and discovered that we could model addition fact families with a sort of abstract version of a number line.</p>
<p>In teaching (actually reteaching) fact families as a springboard into modeling and then writing equations from word problems, I was struck by the difficulty some of my students have with interpreting the equal sign properly. Follow me over the Kroissant.</p>
rss@dailykos.com (Orinoco)Additionequality (math)fact familyMathMathematicsRescuedTeaching_1033404Sat, 05 Nov 2011 19:30:55 UTCNumber Sense 025
http://www.dailykos.com/story/2011/10/29/1031116/-Number-Sense-025
<p>Last week, in <a href="http://www.dailykos.com/story/2011/10/22/1028947/-Number-Sense-024?detail=hide&via=blog_665347">Number Sense 024</a>, we took a look at modeling a simple subtraction, to find out how to produce an equation from a word problem. We ended that essay with a warning that this week we would take up that classic word problem of two trains passing in the night.</p>
<blockquote>A fast train leaves New York at 6 pm and arrives in Boston at 9 pm. A slower train leaves Boston an hour after the first train leaves, and arrives in New York at midnight. If both trains travel non-stop at constant speed, what time do the trains pass each other?</blockquote>
rss@dailykos.com (Orinoco)MathMathematicsmodelTeachingword problems_1031116Sat, 29 Oct 2011 17:27:51 UTCNumber Sense 024
http://www.dailykos.com/story/2011/10/22/1028947/-Number-Sense-024
<p>Last week, in <a href="http://www.dailykos.com/story/2011/10/15/1026588/-Number-Sense-023?showAll=yes&via=blog_665347">Number Sense 023</a>, we took our toy base four number system, figured out its multiplication table, and did a multiplication problem. In California, and most of the rest of the United States, there are standards for teaching mathematics. One of California's standards (and I imagine all states with standards have one similar) is</p>
<blockquote>Communicate precisely about quantities, logical relationships, and unknown values through the use of signs, symbols, <strong>models</strong>, graphs, and mathematical terms.</blockquote>
<p>We see a lot of modeling in this series, on a more or less informal basis (have you ever met a formal goat?) This week, I'd like to take a look at ways to model mathematics problems using simple diagrams developed from the number line.</p>
rss@dailykos.com (Orinoco)fact familyMathMathematicsmodelnumber lineRescuedTeaching_1028947Sat, 22 Oct 2011 16:28:41 UTCNumber Sense 023
http://www.dailykos.com/story/2011/10/15/1026588/-Number-Sense-023
<p>Last week, in <a href="http://www.dailykos.com/story/2011/10/08/1024112/-Number-Sense-022?showAll=yes&via=blog_665347">Number Sense 022</a>, we invented a number system with only four digits, 0, 1, 2 and 3. We were not, of course, the first to have invented this number system, it's well known in the mathematics community as base 4. We figured out how to count in base 4, then we drew a base 4 number line, and finally developed a base four addition facts table and did an addition problem.</p>
<p>This week, I'd like to play a bit more with our toy number system, and use it to multiply.</p>
rss@dailykos.com (Orinoco)Arithmeticbase 4MathMathematicsmultiplicationRescuedTeaching_1026588Sat, 15 Oct 2011 15:15:23 UTCNumber Sense 022
http://www.dailykos.com/story/2011/10/08/1024112/-Number-Sense-022
<p>Last week, in <a href="http://www.dailykos.com/story/2011/10/01/1021840/-Number-Sense-021?showAll=yes&via=blog_665347">Number Sense 021</a>, we took a quick look at place value, an invention that lets us represent very large numbers with only 10 different symbols (0, 1, 2, 3, 4, 5, 6, 7, 8, 9). Sometimes we use the comma when writing very large numbers, so I suppose we could say 11 different symbols. Still, that's a small number of symbols to be able to write numbers into the thousands, millions or billions.</p>
<p>This week I'd like us to take a look at what might happen if we had fewer symbols to use. We will take a look at base 4, that is, a number system that only has four symbols: 0, 1, 2 and 3.</p>
rss@dailykos.com (Orinoco)base 4binaryhexadecimalMathMathematicsoctalRescuedTeaching_1024112Sat, 08 Oct 2011 21:24:37 UTCNumber Sense 021
http://www.dailykos.com/story/2011/10/01/1021840/-Number-Sense-021
<p>Last week, in <a href="http://www.dailykos.com/story/2011/09/24/1019763/-Number-Sense-020?showAll=yes&via=blog_665347">Number Sense 020</a>, we applied the area model, and the distributive property, to do multiplication of large numbers. The numbers weren't very large, they were only two digit numbers, but they were larger than any numbers found in a multiplication table. We couldn't just look up the answer, we had to figure it out.</p>
<p>Methods for figuring out answers that we can't look up are called algorithms, and there are a lot of them. Last week I showed you an algorithm for multiplication called multiplication with partial products. This week I thought I'd take a closer look at place value, an idea that underpins many of the arithmetic algorithms we use today.</p>
rss@dailykos.com (Orinoco)AdditionAlgorithmsextended notationMathMathematicsplace valueTeaching_1021840Sat, 01 Oct 2011 17:18:36 UTCNumber Sense 020
http://www.dailykos.com/story/2011/09/24/1019763/-Number-Sense-020
<p>Last week, in <a href="http://www.dailykos.com/story/2011/09/17/1017632/-Number-Sense-019?showAll=yes&via=blog_665347">Number Sense 019</a>, we took a look at the area model for multiplication, and demonstrated how the distributive property works. I mentioned that this week, we would look at place value notation, or perhaps expanded notation, which is how we write numbers greater than nine.</p>
rss@dailykos.com (Orinoco)area modelMathMathematicsmultiplicationpartial products_1019763Sat, 24 Sep 2011 17:19:20 UTCNumber Sense 019
http://www.dailykos.com/story/2011/09/17/1017632/-Number-Sense-019
<p>Last week, in <a href="http://www.dailykos.com/story/2011/09/10/1015145/-Number-Sense-018?showAll=yes&via=blog_665347">Number Sense 018</a>, we wanted to begin talking about another model for multiplication, the area model, but we made an excursion into geometry, to talk about area, and got sidetracked by some tessellating goats. So, having defined area last week, we are ready to talk about the area model for multiplication this week.</p>
rss@dailykos.com (Orinoco)areacommutative propertydistributive propertyMathMathematicsmultiplicationTeaching_1017632Sat, 17 Sep 2011 17:47:47 UTCNumber Sense 018
http://www.dailykos.com/story/2011/09/10/1015145/-Number-Sense-018
<p>Last week, in <a href="http://www.dailykos.com/story/2011/09/03/1013079/-Number-Sense-017?showAll=yes&via=blog_665347">Number Sense 017</a>, we took a look at the dreaded multiplication table. We discovered that we could get the same result by counting boxes in the multiplication table as we would get by memorizing the table. This is very cool, since we know how to count. This gives us another model for looking at multiplication, the area model. First, we will make a short excursion into geometry, and talk about area.</p>
rss@dailykos.com (Orinoco)math mathematics area tile tesselation_1015145Sat, 10 Sep 2011 17:31:39 UTCNumber Sense 017
http://www.dailykos.com/story/2011/09/03/1013079/-Number-Sense-017
<p>Last week, in <a href="http://www.dailykos.com/story/2011/08/27/1011061/-Number-Sense-016?showAll=yes&via=blog_665347">Number Sense 016</a>, we took a look at adding and subtracting negative integers using our counter and table model. This week, we are going to move on to multiplication, and perhaps see a couple of ways to model that, too.</p>
rss@dailykos.com (Orinoco)MathMathematicsmultiplicationmultiplication tableTeaching_1013079Sat, 03 Sep 2011 17:26:52 UTCRaising taxes on the wealthy does not slow the economy
http://www.dailykos.com/story/2011/08/28/1011063/-Raising-taxes-on-the-wealthy-does-not-slow-the-economy
<p>For decades, you've been living in a world whose economy was defined by the ideas of Jude Wanniski. A political writer turned investment advisor (and blogger), Wanniski never ran for president or even for congress. He didn't head up the federal reserve. He never even had his own sound effects machine on CNBC or a chance to sit next to a wild-eyed blonde on Fox. Despite making a lot of economic forecasts, he wasn't actually an economist. In fact for most of his life the thing that made Wanniski somewhat famous was the fact that he had to leave his post as assistant editor of the <i>Wall Street Journal</i> after being caught handing out material for a Republican candidate, which was a violation of the paper's ethics agreement. Clearly, times have changed.</p>
<p>So what did Wanniski do to become a global economic Illuminati? Well, it was Jude Wanniski who picked up a data-free supposition scrawled on a napkin by freshly-minted PhD Arthur Laffer and popularized it as the "Laffer Curve." It was Jude Wanniski who created the term "supply side economics" and outlined the ideas that others would describe using the terms "trickle down" or (before becoming converted) "voodoo economics." Wanniski designed the tax cuts of the first Reagan administration, developed the theory that it was unsafe for the government to have any cash, and tagged tax policy as the cause for poverty in developing nations. Steve Forbes and Jack Kemp, among others, learned their ideas of flat taxes and government reduction from Wanniski.</p>
<p>This world you live in—the one where people insist that lower taxes generate more jobs and revenue, the one where both congressmen and pundits advocate "starving the beast" that is government, the one where keeping taxes on the rich low because they're "job creators" draws knowing nods, the world in which presidents are elected on the theme that government is the problem—it's Wanniski World. The Reagan Revolution ran on those ideas, so does the Tea Party, and so does a big chunk of what's become "mainstream" economics.</p>
<p>And the problem with all that is... Wanniski was no economist.</p>
<p>Let me hasten to add, neither am I. Please feel free to take everything below with not just a grain of salt, but whole oceans worth of the stuff. The thing is, Wanniski was wrong. Not just a little wrong, 180 degrees wrong. There's very good evidence that George H. W. Bush was right when it came to supply-side economics: it was voodoo all along. The Laffer Curve? Laughable. The idea that coddling the wealthy will make things better for everyone? Backwards.</p>
<p>The core problem with all these ideas is that they start from a bad assumption. No matter how it may seem, the rich are not job creators. That's as true of the guy who owns a factory as it is of the playboy who lives on daddy's yacht. Giving money to those who have money doesn't open up new markets, spur new investments, or spawn new industries.</p>
<p>Jobs come from consumers. It's consumers who create jobs by driving up demand for goods and services. Being a factory owner or a CEO is not the same as being a job creator. No businessman ever created a job because his wallet was a little thicker. It doesn't matter if it's the CEO of Exxon or the winner of the Irish sweepstakes, pouring money into the pockets of the rich does zip-diddly to create jobs, lift the economy, or improve the lot of the average citizen. It most certainly doesn't boost government revenue. Jobs are created when demand calls for it. Revenues go up when the economy grows. Cutting taxes for the wealthy stimulates neither demand nor economic growth.</p>
<p>Henry Ford was wrong about a great number of things, and a bigot on many more, but he wasn't wrong that paying workers higher wages and not keeping all the cash for himself was the key. It doesn't just work for moving Model T's, it works for building a nation. A good tax policy is one that rewards those companies who pay out their wages to the workers and invest their profits in expansion. A bad tax policy is one that retards expansion and damages consumption by encouraging those at the top to take more for themselves. Redistribution of wealth? Sure. <b>All</b> tax policy consists of redistribution of wealth. It's just that current tax policy redistributes that wealth upward—and that's a recipe for disaster.</p>
<p>How can we know that? We know because we've tried it—and not just once. There's an old rule in publishing that states for every graph added to a work, the number of readers is cut in half. By that measure, I'll have about one-twentieth of a reader by the time we get to the end of this, but join me after the jump, loyal left pinky toe of a reader, and I'll try to make it worth your while.<br /></p>
rss@dailykos.com (Mark Sumner)Economicsjude winniskiLaffer CurveSupply Side Economics_1011063Sun, 28 Aug 2011 13:00:46 UTCNumber Sense 016
http://www.dailykos.com/story/2011/08/27/1011061/-Number-Sense-016
<p>Last week, in <a href="http://www.dailykos.com/story/2011/08/20/1008848/-Number-Sense-015?showAll=yes&via=blog_665347">Number Sense 015</a>, we played around with another way of looking at addition and subtraction of integers, using counters instead of a number line. We'll explore that model a bit more this week.</p>
rss@dailykos.com (Orinoco)ArithmeticMathMathematicsTeachingzero pair_1011061Sat, 27 Aug 2011 16:10:56 UTCNumber Sense 015
http://www.dailykos.com/story/2011/08/20/1008848/-Number-Sense-015
<p>Last week, in Number Sense 014, we saw that zero had an interesting property, we can add it to anything and get the same number. Zero is the identity element for addition. At first glance, it seems obvious, and not too useful. Let's see what we can do with such a property.</p>
rss@dailykos.com (Orinoco)MathMathematicsRescuedTeachingzerozero pair_1008848Sat, 20 Aug 2011 15:24:08 UTCHow to read a poll: Confidence intervals and all that
http://www.dailykos.com/story/2011/07/12/993603/-How-to-read-a-poll-Confidence-intervals-and-all-that
<p>Whenever we see a poll, we see a margin of error, or confidence interval. These are always wrong. They are wrong, even if there are only two candidates, and they are even more wrong if there are more than two candidates. But they are simple.</p>
<p>The truth is complicated.</p>
<p>This complication exists even if we assume that the sample is a perfectly random sample of the population of voters. This assumption is ludicrous, but without it, things get really hairy. In fact, the truth is more complicated than this diary makes it out to be</p>
<p>If you have only two candidates then the results follow what is known as a binomial distribution. If you have more than two they follow what is known as a multinomial distribution. "Distribution" is itself a statistical term. It means an assignment of probability to each possible outcome; in this case, the proportion of the vote a candidate will get. In sampling, we try to estimate a population distribution from a sample distribution. Of course, our estimate isn't perfect, but, again assuming it's random, we can estimate how badly off it might be.</p>
<p>There are a few problems with the way margins of error (MoE) are usually presented in polls.</p>
<p>First, we interpret them wrongly. Even if we used the right MoE (see below) our interpretation is off. A confidence interval (CI) is given by the estimate plus or minus the MoE. The correct interpretation of a 95% confidence interval is that, if the population value was X, 95% of the time, the sample value would be in the 95%CI. What we usually assume is that, since the sample estimate is XXX, we can be 95% sure that the population value is within the 95% CI. That's wrong. This interpretation is VERY common; I've even fallen into it myself.</p>
<p>A second wrong interpretation is that we assume either a) That all values within the CI are equally likely or b) That values outside the CI are impossible. Neither is correct. If our poll estimates that 52% will vote for Joe Shmo, then the most likely result is 52%; the farther you go from 52%, the less likely. The likelihood of any particular result is given by the likelihood function - and ANY result from 0 to 100 is possible, it's just that when you get far from 52%, they are very unlikely. (You COULD flip a fair coin 100 times and get 100 heads; it's not LIKELY, but it's POSSIBLE).</p>
<p>But we also give the wrong MoE, because we give a single MoE for each poll, and that's not right. The classical formula for a 95% MoE is</p>
<p>1.96*(pq/n)^.5, </p>
<p>where p is the proportion saying something, q = 1-p and n is sample size.</p>
<p>This is approximately accurate, and the approximation is pretty good for results from polls where n is usually pretty big and we aren't interested in very rare events. It doesn't work well for estimating very rare things, like prevalence of rare diseases, but it's OK for polls. But it gives a different MoE for each candidate. But when there are two candidates who get all (or almost all) of the votes, then this difference doesn't matter too much. For example, if we poll 400 people and 60% say they will vote for Obama, 35% for Bachmann (should she be the Repub. nominee) and 5% for someone else, then the MoE for these three are<br />
Obama 4.88%<br />
Bachmann 4.78%</p>
<p>But the pollsters like to give ONE MoE, so they use an even simpler formula:<br />
0.98/n^.5; this is only exactly correct if p = .5</p>
<p>For the above, it would give<br />
Obama 4.9%<br />
Bachmann 4.9%</p>
<p>not far off.</p>
<p>But what if we are polling a primary? A recent Iowa poll of 500 Repubs gave these results</p>
<p>Bachmann 25%<br />
Romney 21%<br />
Pawlenty 9%<br />
Cain 9%<br />
Paul 6%<br />
Gingrich 4%<br />
Santorum 2%<br />
Huntsman 1%</p>
<p>It said the MoE was 4.4%; that uses the simple formula .98/n^.5. But the right ones, with the formula 1.96*(pq/n)^.5 are different for each candidate and they are</p>
<p>Bachmann 3.8%<br />
Romney 3.6%<br />
Pawlenty 2.5%<br />
Cain 2.5%<br />
Paul 2.1%<br />
Gingrich 1.7%<br />
Santorum 1.2%<br />
Huntsman 0.9%</p>
<p>There are still problems with Huntsman's, but these are much more reasonable figures. They are asymptotically accurate.</p>
rss@dailykos.com (plf515)confidence intervalsDK ElectionsElectionsmargin of errorPolls_993603Tue, 12 Jul 2011 20:06:15 UTCScience, math and statistics books: Open thread
http://www.dailykos.com/story/2011/07/03/991004/-Science-math-and-statistics-books-Open-thread
<p>This is part of a series within the Reading and Book Lovers group; it was suggested by <strong>LimeLite</strong>. The subject is books about science, math and statistics.</p>
<p><strong>This is intended to be a group series, with lots of contributors.</strong> I can't do this alone. But I have a list of topics to get us started, and a list of weeks as well. <br />
This diary will post on Sunday mid-afternoons. I haven't settled on an exact time, and given the nature of Sundays chez plf, I am not sure I can. After brunch/lunch, before dinner.</p>
<p>Topic ideas (some of which could be collaborative with other RBL groupies):</p>
<p>Book reviews regarding science, math and statistics in fiction or non-fiction.</p>
<p>Diaries about popular science writers</p>
<p>Interviews of daily Kos science, math or statistics authors</p>
<p>A community read of a science, math or statistics book, possibly Feynman's The Pleasure of Finding Things Out, or maybe the much neglected Ascent of Man by Jacob Bronowski.</p>
<p>"Why it couldn't happen" - looking at some classic books and why they are not possible.</p>
<p>Books on Kindle or other e-reader vs. paper<br /></p>
rss@dailykos.com (plf515)BooksMathR&BLersReaders & Book LoversReadingScienceSMSBStatistics_991004Sun, 03 Jul 2011 19:00:02 UTCSome thoughts on the teaching of mathematics
http://www.dailykos.com/story/2011/06/30/990263/-Some-thoughts-on-the-teaching-of-mathematics
<p>I love math. I'm a statistician for a living. And I read books about math. It is my firm conviction that more people can like math; that more people ought to like math. They don't, most of them, not out of any innate problem, but because math is the most mistaught subject in the elementary schools and often in the high schools.</p>
<p>Let me ask you something. When you got out of high school, did you know ANY of the following? Which, if any?</p>
<p>1. Euclid's proof that there is no largest prime<br />
2. Stirling's approximation<br />
3, Any infinite series representation of pi<br />
4. A proof that the square root of 2 is irrational<br />
5. A proof of the Pythagorean theorem (not memorizing the formula, but knowing a proof)</p>
<p>And yet, all of these things can be taught based on math that is taught in elementary school.</p>
<p>Let me ask you another question or two</p>
<p>When you got out of high school, had you heard any songs?<br />
Had you seen any paintings?</p>
<p>The fact all (or darn near all) of us have heard many many songs and seen many many paintings is a good thing. The fact that few of us have seen the equivalent in math is a perversion.<br /></p>
rss@dailykos.com (plf515)LearningMathTeaching_990263Thu, 30 Jun 2011 21:31:28 UTCChoosing the red pill: when exp(x) isn't enough
http://www.dailykos.com/story/2011/06/03/977312/-Choosing-the-red-pill-when-exp-x-isn-t-enough
<p><b>Mathematical musings on logarithms, population growth, and sustainability</b></p>
<p>This is another post on sustainability issues inspired by the recent UN report on global population. Sometimes a little high school math can be helpful, and this is one of them. Here's what I'm talking about:<br />
<a href="http://i590.photobucket.com/albums/ss341/blacka5/globpop-1.png?t=1305776545"><img src="http://i590.photobucket.com/albums/ss341/blacka5/globpop-1.png?t=1305776545" /></a></p>
<p>(Data are taken from <a href="http://www.census.gov/ipc/www/worldhis.html">here</a> and updated from <a href="http://www.census.gov/ipc/www/idb/worldpoptotal.php">here</a>.)</p>
rss@dailykos.com (alefnot)eKosEnergyEnvironmentMathpopulation growthRescuedScienceSustainability_977312Fri, 03 Jun 2011 17:05:49 UTCMath, Science and Emotion: Defeating Proposition 8 in 2012
http://www.dailykos.com/story/2011/05/31/980718/-Math-Science-and-Emotion-Defeating-Proposition-8-in-2012
<p>This is a detailed look at the numbers behind the chances of success for the (currently theoretical) effort to repeal Proposition 8 in 2012. Plus a discussion of various other not-so-easily quantifiable factors that could affect the vote.</p>
<p>For those of you not interested in the math, skipping down to the <i>Demographics Isn't Destiny</i> section is advised.</p>
<p>I'll look at three factors that will cause the 2008 vote percentages to change:</p>
<p> -- The effect of teenagers registering to vote<br />
-- The effect of those 65 and older dying<br />
-- The effect social phenomenon might be having on everyone's attitudes<br />
towards same-sex marriage.</p>
<p>For those who just want a brief synopsis, here are the bottom line conclusions:</p>
<ul>
<li>Proposition 8 cannot be defeated in 2012 by age-demographic changes alone.</li>
<li>All evidence points to other factors at work beyond age-demographic change.</li>
<li>The totality of evidence suggests that it is likely that Proposition 8 can be overturned by ballot initiative, but it by no means assured.</li>
<li>Those who want to repeal Proposition 8 have a powerful tool that no one else has been able to avail themselves of. This might be an Ace in the Hole.</li>
</ul>
<br />
rss@dailykos.com (jpmassar)CaliforniaCivil RightsDemographicsEqual RightsLGBTMarriage EqualityPollsProposition 8Recommended_980718Tue, 31 May 2011 17:24:08 UTCScience, math and statistics books: Alan Turing: The Enigma by Andrew Hodges
http://www.dailykos.com/story/2011/04/24/969777/-Science-math-and-statistics-books-Alan-Turing-The-Enigma-by-Andrew-Hodges
<p>This is part of a series within the Reading and Book Lovers group; it was suggested by <strong>LimeLite</strong>. The subject is books about science, math and statistics.</p>
<p>Several weeks ago, in a poll, I asked about who I should cover this week. Alan Turing won, and I am working through a re-read of Alan Turing: The Enigma by Andrew Hodges. But I am not ready to post it yet. So today, I post a book review I previously wrote on Associated Content.</p>
<p>Last week, April 17, Limelite posted about EO Wilson. Thanks Limelite!</p>
<p><strong>This is intended to be a group series, with lots of contributors.</strong> I can't do this alone. But I have a list of topics to get us started, and a list of weeks as well. <br />
This diary will post on Sunday mid-afternoons. I haven't settled on an exact time, and given the nature of Sundays chez plf, I am not sure I can. After brunch/lunch, before dinner.</p>
<p>Topic ideas (some of which could be collaborative with other RBL groupies):</p>
<p>Book reviews regarding science, math and statistics in fiction or non-fiction.</p>
<p>Diaries about popular science writers</p>
<p>Interviews of daily Kos science, math or statistics authors</p>
<p>A community read of a science, math or statistics book, possibly Feynman's The Pleasure of Finding Things Out, or maybe the much neglected Ascent of Man by Jacob Bronowski.</p>
<p>"Why it couldn't happen" - looking at some classic books and why they are not possible.</p>
<p>Books on Kindle or other e-reader vs. paper</p>
rss@dailykos.com (plf515)BooksMathR&BLersReaders & Book LoversReadingScienceSMSBStatistics_969777Sun, 24 Apr 2011 19:00:02 UTCLatest CNN Poll: Majority Support Marriage Equality.
http://www.dailykos.com/story/2011/04/19/968409/-Latest-CNN-Poll-Majority-Support-Marriage-Equality
<p>By a margin of 51% - 47%, the <a href="http://politicalticker.blogs.cnn.com/2011/04/19/poll-more-americans-favor-same-sex-marriage/">latest CNN polling</a> is the most recent in a string of polls showing that Americans' attitudes have shifted to support of marriage equality.</p>
<blockquote><a href="http://i2.cdn.turner.com/cnn/2011/images/04/19/rel6h.pdf">CNN</a>: Do you think marriages between gay and lesbian couples should or should not be recognized by the law as valid, with the same rights as traditional marriages?
<p> Valid: 51%<br />
Not Valid: 47%</p>
<p> Sample: 824 adults.</p>
</blockquote>
<p>There have been at least three other national polls taken in 2011 asking about marriage equality. Here's the results of each of those polls.</p>
rss@dailykos.com (jpmassar)Civil RightsEqual RightsLGBTMarriage EqualityPresident Obama_968409Tue, 19 Apr 2011 19:22:44 UTC(meta) Diary Flow Meter crosses 1000 hours
http://www.dailykos.com/story/2011/04/08/964883/--meta-Diary-Flow-Meter-crosses-1000-hours
<p>In my last diary I announced that the <a href="http://www.dailykos.com/story/2011/02/21/947923/-Diary-flow-rate-meter-is-public">Diary flow rate meter is public</a> and explained what the tool measured and why. I said that I'd let it run for awhile to gather data before making any conclusions. Over fifty megs of data later, I've got some pretty graphs illustrating the rate at which diaries are published on DailyKos, the changes since DK4 was introduced, and answers to some of your most pressing meta questions.</p>
<p><strong>The Diary Flow Gauge</strong><br />
<a href="http://s100.photobucket.com/albums/m35/opendna/?action=view&current=Chart_1.gif" target="_blank"><img src="http://i100.photobucket.com/albums/m35/opendna/Chart_1.gif" border="0" alt="Photobucket" /></a><br />
(DL/RR): the ratio of diaries published to those on the Recently Recommended List. Basically, all of them. :P</p>
rss@dailykos.com (opendna)Diary Flow GaugeDK4MathMathematicsMetaMeta GroupiesStatisticstoolbox_964883Fri, 08 Apr 2011 19:43:12 UTCScience, math and statistics books: A Mathematician's Lament by Paul Lockhart
http://www.dailykos.com/story/2011/04/10/965256/-Science-math-and-statistics-books-A-Mathematician-s-Lament-by-Paul-Lockhart
<p>This is the fourth in a new series within the Reading and Book Lovers group; it was suggested by <strong>LimeLite</strong>. The subject is books about science, math and statistics.</p>
<p>Two weeks ago, in a poll, I asked about who I should cover this week. Alan Turing won, and I am working through a re-read of Alan Turing: The Enigma by Andrew Hodges. But I am not ready to post it yet. So today, I post a book review I previously wrote on Associated Content.</p>
<p>Next week, April 17, Limelite will post about EO Wilson. </p>
<p><strong>This is intended to be a group series, with lots of contributors.</strong> I can't do this alone. But I have a list of topics to get us started, and a list of weeks as well. <br />
This diary will post on Sunday mid-afternoons. I haven't settled on an exact time, and given the nature of Sundays chez plf, I am not sure I can. After brunch/lunch, before dinner.</p>
<p>Topic ideas (some of which could be collaborative with other RBL groupies):</p>
<p>Book reviews regarding science, math and statistics in fiction or non-fiction.</p>
<p>Diaries about popular science writers</p>
<p>Interviews of daily Kos science, math or statistics authors</p>
<p>A community read of a science, math or statistics book, possibly Feynman's The Pleasure of Finding Things Out, or maybe the much neglected Ascent of Man by Jacob Bronowski.</p>
<p>"Why it couldn't happen" - looking at some classic books and why they are not possible.</p>
<p>Books on Kindle or other e-reader vs. paper</p>
<p>The RBL schedule</p>
<p>The RBL schedule:<br /></p>
<table cellspacing="1" cellpadding="2" border="3" width="600">
<tr>
<td><b>DAY</b></td>
<td><b>TIME (EST/EDT)</b></td>
<td><b>Series Name</b></td>
<td><b>Editor(s)</b></td>
</tr>
<tr>
<td><b>SUN</b></td>
<td>3:00 PM</td>
<td><i>Science, Math, and Statistics Books</i></td>
<td>plf515</td>
</tr>
<tr>
<td>SUN</td>
<td>8:00 PM</td>
<td><i>Publish Your Own Kindle Book</i><br />
(mini-series)</td>
<td>bink</td>
</tr>
<tr>
<td>SUN</td>
<td>9:30 PM</td>
<td><i>SciFi/Fantasy Book Club</i></td>
<td>quarkstomper</td>
</tr>
<tr>
<td>SUN</td>
<td>Late Nite</td>
<td><i>My Reading Life</i></td>
<td>various</td>
</tr>
<tr>
<td><b>MON</b></td>
<td>8:00 AM</td>
<td><i>And the Winner Is. . .</i></td>
<td>88kathy</td>
</tr>
<tr>
<td>MON</td>
<td>11:00 AM</td>
<td><i>eReader Cafe</i></td>
<td>Dichro Gal</td>
</tr>
<tr>
<td><b>TUE</b></td>
<td>Noon</td>
<td><i>The Mad Logophile</i> (bi-weekly)</td>
<td>Purple Priestess</td>
</tr>
<tr>
<td>TUES</td>
<td>8:00 PM</td>
<td><i>Readers & Book Lovers Newsletter</i></td>
<td>Limelite</td>
</tr>
<tr>
<td><b>WED</b></td>
<td>7:00 AM</td>
<td><i>WAYR?</i></td>
<td>plf515</td>
</tr>
<tr>
<td>WED</td>
<td>8:00 PM</td>
<td><i>Bookflurries: Bookchat</i></td>
<td>cfk</td>
</tr>
<tr>
<td><b>THU</b></td>
<td>11:00AM</td>
<td><i>Books for Young Adults and Children (BYAC)</i></td>
<td>Dichro Gal</td>
</tr>
<tr>
<td>THU</td>
<td>8:00PM</td>
<td><i>Write On!</i></td>
<td>SensibleShoes</td>
</tr>
<tr>
<td><b>FRI</b></td>
<td>9:00 AM</td>
<td><i>Books That Changed My Life</i></td>
<td>etbnc, aravir</td>
</tr>
<tr>
<td><b>SAT</b></td>
<td>12 Noon</td>
<td><i>Let’s Write a Story</i></td>
<td>mdmslle</td>
</tr>
<tr>
<td>SAT</td>
<td>2:00 PM</td>
<td><i>DK Political Book Club</i></td>
<td>Freshly Squeezed Cynic</td>
</tr>
<tr>
<td>SAT</td>
<td>9:00 PM</td>
<td><i>Books So Bad They're Good</i></td>
<td>Ellid</td>
</tr>
</table>
<table>
<tr>
<td><b>Intermittent Diaries</b></td>
</tr>
<tr>
<td><b>SUN</b></td>
<td>?</td>
<td><i>Justice, Not Charity</i></td>
<td>Runaway Rose, allie123</td>
</tr>
<tr>
<td><b>MON</b></td>
<td>Late Nite</td>
<td><i>Literature for Kossacks</i></td>
<td>Pico</td>
</tr>
</table>
rss@dailykos.com (plf515)BooksMathR&BLersReaders & Book LoversReadingScienceSMSBStatistics_965256Sun, 10 Apr 2011 19:00:02 UTCMultivariate analysis of Wisconsin recalls
http://www.dailykos.com/story/2011/03/27/960679/-Multivariate-analysis-of-Wisconsin-recalls
<p>(Cross-posted at <a href="http://www.swingstateproject.com/diary/8589/multivariate-analysis-of-wisconsin-polling-data">SSP</a>)</p>
<p>A couple weeks ago, Kos/PPP polled all the Wisconsin Republicans up for recall and found <a href="http://www.dailykos.com/story/2011/03/15/956357/-Wisconsin-recall:-3-GOP-state-senators-trail-Generic-Dem,-more-at-risk">some very interesting results</a>. However, he did not poll the Dem races up for recall, as well as the statewide upcoming Supreme Court race. In an attempt to rectify this fault, although I'm no Poblano, I decided to try to use multivariate regression to try and model the Wisconsin polling data using information from each district.</p>
rss@dailykos.com (Michiganliberal)David ProsserJim HolperinMathStatisticsWisconsinWisconsin RecallWisconsin Senate_960679Sun, 27 Mar 2011 21:20:49 UTCSilver vs. Enten on 2012 House
http://www.dailykos.com/story/2011/03/27/960221/-Silver-vs-Enten-on-2012-House
<p>Last week a political statistics blogger, Harry Enten, published a <a href="http://poughies.blogspot.com/2011/03/republicans-to-maintain-control-of.html">forecast</a> of the 2012 House race, estimating that the Republicans will win 238 seats. He estimated a standard error of only about 5 seats in this prediction, and said the odds of the Democrats regaining control (218 seats) were very low. Nate Silver <a href="http://fivethirtyeight.blogs.nytimes.com/">criticized</a> Enten's prediction. Nate's central point was that Enten has used a large number of variables (6), not specified by some clear prior theory, to fit a small number of data points (15). Such procedures are famous for producing unrealistically small error bars. Enten has since <a href="http://poughies.blogspot.com/">responded</a>, trying to justify his original claims.</p>
<p>There is really no contest in this debate. Silver's basic criticisms are all correct. The model uses special-pleading variables concerning highly specified types of wars in order to obtain its remarkable fit. Enten hasn't done the basic tests (jackknife,...) of the model for robustness. Silver tried a simple test- seeing if it could be extended back to retrodict the election (1948) just before those in the data set used. The model failed dramatically.</p>
<p>I just want to add one other point. Enten assumes a Gaussian distribution of errors in calculating his probabilities. Nate followed the logic of that assumption to point out that the model implied a 1/100,000 chance of a Democratic win. In his response, Enten did not challenge that extrapolation, so apparently that is indeed what he meant to imply. Gaussians are wonderful things when they are justified, but this is a classic case where there is no justification at all. The probability calculations are nonsense. Implicitly, in parallel with the pseudo-precise math, Enten acknowledges that the structure of his probability calculation (in particular the Gaussian distribution) is unfounded, in that he says the prediction could be altered by an ill-defined "historic event", with no quantification of how often those happen.</p>
<p>Does this mean that the odds instead favor the Democrats to retake the House? No, the gambling markets have a pretty good track record, and they favor the Republicans. Enten's guess as to the most likely result isn't any worse than anybody else's. It does mean that his statistical probabilities are bogus. In this case, that's good news, since the gamblers agree with common sense that the Democrats have a fairly good shot.</p>
rss@dailykos.com (docmidwest)ElectionsPolls_960221Sun, 27 Mar 2011 16:30:13 UTC