Ethics, Quants and Cold-Calling - Bloomberg
As far as I can tell, the pitch for data scientists from Silicon Valley is: "Come work here, you can build advertising models and pretend that you're saving the world," while the pitch for data scientists from Wall Street is: "Come work here, you can build trading models and not have to pretend that you're saving the world." I actually think that is a useful sorting metric, and I know which one I would take.
finance  datascience 
3 days ago
Econometrics Beat: Dave Giles' Blog: Micronumerosity
"Econometrics texts devote many pages to the problem of multicollinearity in multiple regression, but they say little about the closely analogous problem of small sample size in estimation a univariate mean. Perhaps that imbalance is attributable to the lack of an exotic polysyllabic name for 'small sample size'. If so, we can remove that impediment by introducing the term micronumerosity.

Suppose an econometrician set out to write a chapter about small sample size in sampling from a univariate population. Judging from what is now written about multicollinearity, the chapter might look like this:

1. Micronumerosity
The extreme case, 'exact micronumerosity', arises when n = 0; in which case the sample estimate of μ is not unique. (Technically, there is a violation of the rank condition n > 0: the matrix 0 is singular.) The extreme case is easy enough to recognize. 'Near micronumerosity' is more subtle, and yet very serious. It arises when the rank condition n > 0 is barely satisfied. Near micronumerosity is very prevalent in empirical economics.
statistics  humour 
8 weeks ago
The Long Con - Rick Perlstein on Republicans and lying
These are bedtime stories, meant for childlike minds. Or, more to the point, they are in the business of producing childlike minds. Conjuring up the most garishly insatiable monsters precisely in order to banish them from underneath the bed, they aim to put the target to sleep.
And that, at last, may be the explanation for Mitt Romney’s apparently bottomless penchant for lying in public. If the 2012 GOP nominee lied louder than most—and even more astoundingly than he has during his prior campaigns—it’s just because he felt like he had more to prove to his core following. Lying is an initiation into the conservative elite. In this respect, as in so many others, it’s like multilayer marketing: the ones at the top reap the reward—and then they preen, pleased with themselves for mastering the game. Closing the sale, after all, is mainly a question of riding out the lie: showing that you have the skill and the stones to just brazen it out, and the savvy to ratchet up the stakes higher and higher. Sneering at, or ignoring, your earnest high-minded mandarin gatekeepers—“we’re not going to let our campaign be dictated by fact-checkers,” as one Romney aide put it—is another part of closing the deal. For years now, the story in the mainstream political press has been Romney’s difficulty in convincing conservatives, finally, that he is truly one of them. For these elites, his lying—so dismaying to the opinion-makers at the New York Times, who act like this is something new—is how he has pulled it off once and for all. And at the grassroots, his fluidity with their preferred fables helps them forget why they never trusted the guy in the first place.
politics  usa  republican  advertising 
8 weeks ago
The Crisis of Attention Theft—Ads That Steal Your Time for Nothing in Return | WIRED
“I tremble for the sanity of a society that talks, on the level of abstract principle, of the precious integrity of the individual mind, and all the while, on the level of concrete fact, forces the individual mind to spend a good part of every day under bombardment with whatever some crowd of promoters want to throw at it.”
advertising  economics 
9 weeks ago
CS 228 notes
These notes form a concise introductory course on probabilistic graphical models. Probabilistic graphical models are a subfield of machine learning that studies how to describe and reason about the world in terms of probabilities. . They are based on Stanford CS228, taught by Stefano Ermon, and are written by Volodymyr Kuleshov, with the help of many students and course staff.
statistics  probability 
9 weeks ago
jtleek/datasharing: The Leek group guide to data sharing
To facilitate the most efficient and timely analysis this is the information you should pass to a statistician:

The raw data.
A tidy data set
A code book describing each variable and its values in the tidy data set.
An explicit and exact recipe you used to go from 1 -> 2,3
datascience  statistics 
10 weeks ago
Reproducible Data Analysis in Jupyter | Pythonic Perambulations
Jupyter notebooks provide a useful environment for interactive exploration of data. A common question I get, though, is how you can progress from this nonlinear, interactive, trial-and-error style of exploration to a more linear and reproducible analysis based on organized, packaged, and tested code. This series of videos presents a case study in how I personally approach reproducible data analysis within the Jupyter notebook.
jupyter  python 
10 weeks ago
The Long, Lucrative Right-wing Grift Is Blowing Up in the World's Face
Rather rapidly, two things happened: First, Republicans realized they’d radicalized their base to a point where nothing they did in power could satisfy their most fervent constituents. Then—in a much more consequential development—a large portion of the Republican Congressional caucus became people who themselves consume garbage conservative media, and nothing else.

That, broadly, explains the dysfunction of the Obama era, post-Tea Party freakout. Congressional Republicans went from people who were able to turn their bullshit-hose on their constituents, in order to rile them up, to people who pointed it directly at themselves, mouths open.
politics  trump  media  usa 
10 weeks ago
The DADSS Midterm Grading Procedure
score = 1 + ln(p)/ln(4), where p is probability you assign to correct answer
statistics  probability  education 
10 weeks ago
Equal pay: New York banned employers from asking job candidates about past salaries - The Washington Post
The New York City Council isn't fond of it, either. In a vote Wednesday, it approved legislation that will ban employers from asking job applicants about what they make in their current or past job and could have far-reaching consequences beyond the city as employers try to standardize their practices. It's an idea that's starting to spread: In passing the measure, New York City joins Massachusetts, Puerto Rico and the city of Philadelphia — where the local Chamber of Commerce filed a lawsuit against that measure Thursday — in banning the question from job interviews. More than 20 other city and state legislatures have introduced similar provisions.
professional  sexism 
10 weeks ago
Why bots aren’t the real AI disruption – Textio Word Nerd
Many of today’s bots are kind of a hipster façade around the same basic command line interfaces consumers abandoned in the 1980s. They require specific syntaxes and understand only a limited vocabulary—but they sure have personality!
While the added convenience of language recognition is a benefit, until bots are capable of performing very complex and novel tasks that richly combine actions and context across the boundaries of apps and sites in unique ways the first time they are asked, we will be limited to trying to remember the 489 commands Siri recognizes. (Yes that link is a man page for Siri. ~sigh~)
bot  ai  machinelearning 
10 weeks ago
Astronomers explore uses for AI-generated images : Nature News & Comment
"Generative AIs look promising for basic science, too, says Welling, who is helping to develop software for the Square Kilometre Array (SKA), a radio-astronomy observatory to be built in South Africa and Australia. The SKA will produce such vast amounts of data that its images will need to be compressed into low-noise but patchy data. Generative AI models will help to reconstruct and fill in blank parts of those data, producing the images of the sky that astronomers will examine.

A team led by Rachel Mandelbaum, an astrophysicist at Carnegie Mellon University, has been experimenting with both GANs and VAEs to simulate images of galaxies that look deformed because of gravitational lensing — when the gravity of objects in the foreground distorts space-time and warps light rays. Researchers are planning to survey huge numbers of galaxies to map gravitational lensing across the Universe’s history. This could show how the distribution of the Universe’s matter has changed over time, providing clues to the nature of the dark energy that is thought to have driven cosmic expansion. But to do this, astronomers need software that can reliably separate gravitational lensing from other effects. Synthetic images will improve the programs’ accuracy, Mandelbaum says."

gans  neuralnetworks  astro 
10 weeks ago
The Corporation Does Not Always Have To Win
You are not the corporation. You are the human. It is okay for the corporation to lose a small portion of what it has in terrifying overabundance (money, time, efficiency) in order to preserve what a human has that cannot ever be replaced (dignity, humanity, conscience, life). It is okay for you to prioritize your affinity with your fellow humans over your subservience to the corporation, and to imagine and broker outcomes based on this ordering of things. It is okay for the corporation to lose. It will return to its work of churning the living world into dead sand presently.
business  usa  capitalism 
11 weeks ago
« earlier      
1970s 20c 21c 2fa 401k abc abtesting academia accommodation adtech advertising ageism ai airbnb algorithms amazon amiga analytics anecdata anglican anomaly ansible antarctica api apple architecture art arxiv asia astro astronomy asyncio auc audio autism awk aws backup badscience banking bash basketball bayes bayesdb bias bigdata bitcoin book books bot bottle brexit britain brooklyn bug business c california camera capitalism car charity chess children china chrome cia civilrights climate climatechange clojure code colonialism communication communism computers concurrency conference coroutines cosmology crime cryptocurrency cryptography cs css csv culture cycling cython dancing darkmatter data database dataengineering datascience datasets datastructures death debt deeplearning design development devops diversity diy docker earth ebay economics education elsevier email emoji emulation engineering english entityresolution equity erlang espionage ethics etsy eu europe f# facebook facism fairness family fashion fastforward fatml feminism film finance finland fintech frontend functional fzf gambling gans gaussianprocesses gawker gchq geography germany gerrymandering gif gis gist git github globalentry golang google government gpu gradschool grammar graph greece grep gui h1b hardware haskell hawaii health hiring history hmm home homomorphic housing html http humor humour hype ibm image immigration infrastructure insight instagram insurance internet interpretability interview investments ipython iraq java javascript job jobs journal journalism js json julia jupiter jupyter kdb keras korean kubernetes labour lambda language law lda lectures legal lendingclub liberalarts liberalism linearalgebra linguistics linux lisp literature logic london losangeles lstm mac machinelearning macos make management map mapreduce maps marfa marketing mars math maths me mechanicalturk media medicine mfa microsoft military mining module money mp3 mta music mxnet name nazism network networking neuralnetworks neuroscience newyork next nips nist nlg nlp nosql notebook npr nsa nuclear numpy nyc obama oop opensource os oxford p2ploans package pandas paypal pdf philanthropy philosophy phone phonetics photography photoshop php physics pivot planning poem politics polling postgresql poverty presentation privacy probabilisticprogramming probability product professional programming pronunciation psephology publishing pymc3 pystan pytest python pywren q quant quantum r race racism radio reading rec recipe recommendation reinforcementlearning relationships religion remote republican research rest review ripgrep rnn robots.txt roc russia rust salary sanfrancisco satellite scala scheme science sciencewriting scientism scikitlearn scipy search security sed semisupervised sentiment serverless sexism sf siliconvalley slack smalldata social socialism socialmedia solarsystem sonos space spacy spark sql ssh ssl stan startup startups statistics stream study style suburban supervised switzerland sysadmin talk tax teaching tech technology tensorflow terrorism testing texas text theano thesis time timemachine timeseries tmux tox translation transport travel trump tsne tts tutorial tv twitter typography uber uk unicode unions unix unsupervised urban usa usage usps ux vc versioncontrol video vim virtualenv visa visualization vpn weather web webdev windows word2vec wsgi

Copy this bookmark: