Источник
Выбор редакции
16 августа, 21:41

Без заголовка

  • 0

**Live from the Orange-Haired Baboon Cage**: Silver Lining Department : One piece of good news from the past week: we now know that the president and his camarilla are not secret Nazis. Secret Nazis are always much more eager to denounce Nazi violence than Trump turns out to be. That is the whole point of being a _secret_ Nazi: you keep your Nazi sympathies secret! Nathan Bedford Forrest was much more eager to denounce the Ku Klux Klan than Donald Trump is to denounce the alt right. And Nathan Bedford Forrest was the leader and founder of the Ku Klux Klan! The whole "plausible deniability" thing is now out the window. And no American can now pretend that it is not there or that if they ignore it it will go away...

Выбор редакции
16 августа, 21:37

Yes, Virginia, Things Will Probably Get Better...

  • 0

**Live from America's Better Self**: Orientation Day : Yesterday we had 750 groups of about 20 people each following standards around the campus: The Berkeley freshmen are here. Young, smart very idealistic, many very upwardly mobile, somewhat scared, very excited—at the prospect of being no longer children but themselves, and grown-ups. You look at them, and you have to think America is very great indeed. It is a very refreshing change from looking at the White House, or the congressional majorities, or the speakers on Fox News: terrifying their elderly viewers to keep their eyeballs glued to the TV set so that they can be sold overpriced gold funds and fake medicines endorsed by republican bigwigs like Huckabee and Carson...

Выбор редакции
16 августа, 20:32

Без заголовка

  • 0

**Should-Read: Drew Conway**: The Data Science Venn Diagram : "The primary colors of data: hacking skills, math and stats knowledge, and substantive expertise... >...each... very valuable, but when combined with only one other are at best simply not data science, or at worst downright dangerous.... Being able to manipulate text files at the command-line, understanding vectorized operations, thinking algorithmically... the hacking skills... apply[ing] appropriate math and statistics methods... [but] data plus math and statistics only gets you machine learning, which is great if that is what you are interested in, but not if you are doing data science... [which] is about discovery and building knowledge.... >The hacking skills plus substantive expertise danger zone... people who “know enough to be dangerous”... capable of extracting and structuring data... related to a field they know quite a bit about and... run a linear regression... lack[ing] any understanding of what those coefficients mean. It is from this part of the diagram that the phrase “lies, damned lies, and statistics” emanates, because either through ignorance or malice this overlap of skills gives people the ability to create what appears to be a legitimate analysis without any understanding of how they got there or what they...

Выбор редакции
16 августа, 20:27

Без заголовка

  • 0

**Note to Self**: _"Data Science" as an Ephemeral Term_:There was a time—perhaps a century, maybe a bit more, certainly not much less—ago, when the high-tech bleeding edge electricity sector was an important but discrete part of the "economy". Today, if one asks: "Where is the electricity sector? What is the impact of electricity on the economy?"; the only possible answer today is: "Everywhere". Electricity is no longer in any sense any sort of discrete sector. Electricity is _everywhere_. So it is rapidly becoming with computers and "data science". Computers, data, simulations, understanding systems via emergence from the bottom-up, communication—they are no longer a discrete piece of our society and our educational system. Already they are intermixed. Soon they will be everywhere. Soon it will make as little sense to talk about the discrete pieces of the university that make use of computers as it makes sense to talk about the discrete pieces of the university that use electricity. But how soon? How long is the expected lifespan of Berkeley's [Division of Data Sciences][]? How long before it either eats the rest of the college—as everything becomes data science—or sublimes into the rest of the college—as everything becomes data science? [Division...

Выбор редакции
16 августа, 20:25

Без заголовка

  • 0

**Note to Self**: I am told that what we are doing here is something called "data science"... I find myself feeling somewhat surprised—like the "Middle-Class Aristocrat" title character in 1600s-era French playwright [Moliêre's][] _[Le Bourgeois Gentilhomme][]_, who is astonished and gratified to learn that he has, his entire life, been a master of that highbrow literary accomplishment of speaking "prose": "Well, what do you know about that! These forty years now I’ve been speaking in prose without knowing it!" I had thought that I was simply: * Studying and analyzing cases to understand how pieces of the world worked. * Counting and aggregating statistical totals to understand which case studies were in fact broadly representative of the world as a whole. But I am now told that this is "data science": the combination of substantive expertise in my particular area, the ability to use mathematical and statistical tools properly and sensibly, plus knowing how to make my computers dance (or, rather, shamble forward in a stumbling zombie-like walk). So let me roll with it and see where it takes us... [Moliêre's]: https://en.wikipedia.org/wiki/Molière [Le Bourgeois Gentilhomme]: https://en.wikipedia.org/wiki/Le_Bourgeois_gentilhomme

Выбор редакции
16 августа, 20:23

Без заголовка

  • 0

**Note to Self: Data Science Reading List**: * **John Tukey**: The Future of Data Analysis: "Large parts of data analysis are inferential... but only parts.... Large parts... are incisive.... Some parts... are allocative... dude its in the distribution of effort..." * **Leo Breiman**: Statistical Modeling: The Two Cultures: "The data are generated by a given stochastic data model... [vs.] algorithmic models... treat[ing]... the data mechanism as unknown. The statistical community['s]... commit[ment]... to... models... has led to irrelevant theory, questionable conclusions, and has kept statisticians from working on a large range of interesting current problems..." * **Ben Fry**: computational information design: "Fields such as information visualization, data mining and graphic design... each solv[e]... an isolated part of the specific problem but fail... in a broader sense.... This dissertation proposes that the individual fields be brought together as part of a singular process titled Computational Information Design..." * **Hal Varian**: How the Web challenges managers: "There’s already been a big revolution in how we view intellectual property.... It’s not so much the question of what’s owned or what’s not owned. It’s a question of how can you leverage the assets you have to realize the most value.... Disseminating content... has become intensely...

Выбор редакции
16 августа, 20:23

Без заголовка

  • 0

**Note to Self**: View jupyter notebook from dropbox (or other) links: * Dropbox: change: "https://www.dropbox.com/" to: "http://nbviewer.jupyter.org/urls/dl.dropbox.com/"; then load the url... * Else: change: "https://" to "http://nbviewer.jupyter.org/"; then load the url...

11 августа, 03:52

Без заголовка

  • 0

**Should-Read: Economist**: Who will be the next chair of the Federal Reserve?: "The interest-rate opinions of the favourite to succeed her are less clear. Mr Cohn... >...thinks that monetary policy is a global endeavour, and that central banks may have been playing beggar-thy-neighbour. In March 2016 he told a conference that if every central bank suddenly raised interest rates by three percentage points, “the world would be a better place”. Yet he also said he was not sure Ms Yellen had been right to raise rates three months earlier. And he criticised the Fed’s recent forward guidance as confusing for the markets. He said it should worry more about what it does than what it says. >The Fed is not only responsible for monetary policy. It is also the biggest regulator of banks. Here Mr Cohn is more in sync with Mr Trump’s deregulatory agenda. However, that may not matter much. The president recently nominated Randal Quarles, another critic of recent regulation, to be vice-chairman for supervision, a post left empty since it was created in 2010 (though in practice the job was done by Daniel Tarullo, who left the Fed in April). Whoever heads the Fed, Mr Quarles will...

Выбор редакции
11 августа, 03:49

Без заголовка

  • 0

**Live From Berkeley**: In the Academic Innovation Studio; Unique challenges of teaching large enrollment courses * Dwinelle 117 * Thursday, August 10 * 2:30 p.m. to 4:00 p.m. Open and informal conversation. Light refreshments. Bring your questions, experience, suggestions, and successes to share with colleagues and generate new ideas for your own teaching.

Выбор редакции
11 августа, 03:49

Ten Years and Eleven Days Ago on Grasping Reality: July 31, 2007

  • 0

**Worth Highlighting:** * Felix Salmon starts to see the train coming: Felix Salmon on Noise--Literally: Noise--Traders : He watches Jim Cramer, and is scared: "Great Moments in Punditry: Jim Cramer on Housing: Is it worth responding to this as though it's rational? Is this what passes for informed commentary on TV these days? I can see how it gets ratings, in a train-wreck kind of way–hell, I'm blogging it. But the idea that wealthy people will stop paying their mortgages because their houses are 'fungible' (unless we get a 100bp cut in the Fed funds rate, of course)–it's like some kind of incredibly unfunny parody. Nouriel Roubini et al might be shrill, but at least there's coherent logic to their position. What scares me is that this could be a rare and genuine glimpse into how traders actually think. In which case the Great Moderation and decline in volatility of recent years is doomed to die a sudden and extremely unpleasant death..." * No, Fox News has always been a slough of iniquity. Why do you ask?: Why Oh Why Can't We Have a Better Press Corps? (Bill O'Reilly Edition) : Atrios tells us that it is Felafel Day, and...

Выбор редакции
11 августа, 03:43

Без заголовка

  • 0

**Should-Read: Fabio Ghironi**: Micro Needs Macro: "An emerging consensus on the future of macroeconomics views the incorporation of a role for financial intermediation, labor market frictions, and household heterogeneity in the presence of uninsurable unemployment risk as key needed extensions to the benchmark macro framework... >...I argue that this is welcome, but not sufficient for macro and international macro to tackle the menu of issues that have been facing policymakers since the recent global crisis. For this purpose, macro needs more micro than the benchmark setup has been incorporating so far. Specifically, artificial separations between business cycle analysis, the study of stabilization policies, and growth macro, as well as between international macroeconomics and international trade, must be overcome. I review selected literature contributions that took steps in this direction; outline a number of important, promising directions for future research; and discuss methodological issues in the development of this agenda...

Выбор редакции
11 августа, 03:39

Без заголовка

  • 0

**Should-Read: Nancy MacLean**: Democracy in Chains: The Deep History of the Radical Right's Stealth Plan for America : "As 1956 drew to a close, Colgate Whitehead Darden Jr., the president of the University of Virginia, feared... >...second Brown v. Board of Education ruling, calling for the dismantling of segregation in public schools with “all deliberate speed.” In Virginia, outraged state officials responded with legislation to force the closure of any school that planned to comply.... Darden... could barely stand to contemplate the damage.... Even the name of this plan, “massive resistance,” made his gentlemanly Virginia sound like Mississippi. >On his desk was a proposal, written by the... chair of the economics department... James McGill Buchanan [who] liked to call himself a Tennessee country boy. But Darden knew better.... Without mentioning the crisis at hand, Buchanan’s proposal put in writing what Darden was thinking: Virginia needed to find a better way to deal with the incursion on states’ rights represented by Brown. >To most Americans living in the North, Brown was a ruling to end segregated schools—nothing more, nothing less. And Virginia’s response was about race. But to men like Darden and Buchanan, two well-educated sons of the South who were...