• Parallel Sets for categorical data, D3 port

    May 3, 2012  |  Statistical Visualization

    Parallel sets

    A while back, Robert Kosara and Caroline Ziemkiewicz shared their work on Parallel Sets, a way to visually explore categorical data. Software developer, Jason Davies, just ported the technique to Data-Driven Documents (D3). The interactions for sorting and rearranging are similar to the Kosara and Ziemkiewicz version, but the D3 version of course runs in the browser and has some nifty transitions. Try toggling the show curves box and the icicle plot one.

  • How recruiters look at your resume

    April 11, 2012  |  Statistical Visualization

    Recruiters looking at resumes

    In a study by TheLadders (of n equals 30), recruiters looked at resumes and make some judgments. During evaluations, eye tracking software was employed, and they found that the recruiters spent about six seconds on a resume looking for six main things: name, current company and title, previous company and title, previous position start and end dates, current position start and end dates, and education. After that, it was a crapshoot.

    Beyond these six data points, recruiters did little more than scan for keywords to match the open position, which amounted to a very cursory "pattern matching" activity. Because decisions were based mostly on the six pieces of data listed above, an individual resume’s detail and explanatory copy became filler and had little to no impact on the initial decision making. In fact, the study’s eye tracking technology shows that recruiters spent about 6 seconds on their initial "fit/no fit" decision.

    If I ever have to submit a resume, I'm just going to put those six things as bullets and then the rest will all be keywords in small, light print. It'll be like job search SEO.

    Update: I've been told that TheLadder's reputation might be less than savory, and a quick search shows some in agreement, so it might be wise to sidestep the service. Instead, go with my awesome six-bullet advice and you're gold.

    [via @alexlundry]

  • Towards a Low-carbon World

    March 20, 2012  |  Statistical Visualization

    low-carbon economy

    Carbon output. We want to reduce it, but some countries have a longer way to go than others. Pitch Interactive shows progress (or non-progress) by country in this interactive for the Climate Institute. Three indices are shown along with an overall score, which is a composite of the three, and countries are sorted by the average score from 1995 to 2008. Higher scores are better.

    The interaction makes this graphic. When you switch between indices, the countries are sorted appropriately and the time series for each country are drawn. You can also click on a country to get a closer view, which albeit is only four data points per country and index, but it's still useful.

    The lines for each country get thicker from left to right, which was to provide a sense of progress, but I wonder if it would be worthwhile to use thickness to represent an increase or decrease from the previous year. Then again, that's easy enough to see already, so maybe not.

  • Odds of losing in roulette

    March 13, 2012  |  Statistical Visualization

    Roulette single bet odds

    Jay Jacobs has some fun with roulette simulations and explores the odds of winning for different bets. Above shows a simulation of 250 spins 20,000 times. Or to put it differently, it's like simulating the play of 20,000 people, who each took 250 spins and always bet on a single number.

    I'm not sure why it doesn't start to get red until you're $500 in the hole, but bottom line: the longer you play, the higher probability you will lose all your money. That was my main takeaway from Probability 101 in undergrad. The rest is a blur.

  • Who voted for Santorum and Romney

    March 9, 2012  |  Statistical Visualization

    As a complement to Shan Carter's exit poll dancing boxes, The New York Times provides another view with an interactive triangular scatterplot.

    In the dancing boxes, you can see how states are inclined to vote based on exit poll groups. In the scatterplot, on the other hand, the groups within each state are plotted, with an added dimension towards candidates other than Santorum and Romney. The navigation bar on top and clicker on the left let you see tendencies of each state.

    Like the dancing boxes, the transitions make the chart. As you browse by state or by category, you're able to see differences between groups when shapes move across the screen.

    In somewhat related news, The New York Times graphics department is looking for summer interns. Send your interest to Steve Duenes (duenes [at] nytimes [dot] com) and Amanda Cox (coxa [at] nytimes [dot] com). I interned there a few years ago, so I can tell you first-hand that you'll learn a lot — probably more than in any class you've taken — while working with the best in the business.

    [New York Times]

  • Thomas the Tank Engine and Friends, accidental chart

    March 6, 2012  |  Statistical Visualization

    Thomas the train

    This came via Twitter from @christopferd:

    Will @flowingdata caption my 2 yr old's first [accidental] chart with his #thomas trains?

    How could I resist? You gotta get 'em while they're young. I added the labels, mostly to show off my expansive knowledge of Thomas the Train Tank Engine and Friends.

  • Slicing Obama’s 2013 budget proposal four ways

    February 15, 2012  |  Statistical Visualization

    budget views

    With Obama's recent budget for next year proposed, Shan Carter et. al of The New York Times let you explore the plan in their new interactive. It provides four distinct views of what the breakdowns look like, all the while keeping a distinct link between each click with smooth transitions and consistent objects (much of which was handled with Mike Bostock's D3).

    Initially, a view of all spending is shown at once. Each bubble represents a chunk of spending, and each is colored by the change from last year. Green shows more money and red means less, and as indicated on the chart, spending is oriented from largest increase to largest cut, top to bottom.

    Next tab: types of spending. This is when the magic happens. Instead of skipping to a new graphic, the existing bubbles divide to show mandatory and discretionary spending. Jump to the next view to see changes to discretionary spending, and finally see spending shown by department.

    The transitions make this graphic. It's often useful to see data from different angles, and the smooth transitions (rather than abrupt jumps) let you see how things are and how they have changed, effectively. This is fine work.

    [New York Times]

  • Compare presidential candidate fundraising

    February 2, 2012  |  Statistical Visualization

    Money race with candidates

    Presidential candidates have raised $186 million up to now, according to the Federal Election Commission. The New York Times lets you compare the amounts raised by each candidate, over time and space. Simply select a candidate on the left, and another on the right to see how they match up. Fundraising by candidates from previous elections, at the same time of year, are also included for context.

    While not the focus of the interactive, the distributions for donation size at the bottom seem to be especially telling.

    [New York Times via infosthetics]

  • Words used in SOTU and Republican presidential candidates in debates

    January 24, 2012  |  Statistical Visualization

    Choice words

    Jonathan Corum for The New York Times examines word usage by President Barack Obama in his State of the Union addresses and the words used by Republican candidates in their debates. Many of you will be happy to know that no word clouds were harmed in the making of this graphic.

    [New York Times]

  • Job growth at the best companies to work for

    January 24, 2012  |  Statistical Visualization

    Job Growth

    Nicolas Rapp and Anne Vandermey with a straightforward look at new jobs added at the top 100 companies to work for, according to Fortune.

    Fat paychecks, sweet perks, fun colleagues, and over 70,000 jobs ready to be filled — these employers offer dream workplaces. Like Google, which reclaims the top spot this year to become a three-time champion. Meet this year’s top 100, network with the winners on LinkedIn, and more.

    Number of new jobs added or lost is on the horizontal, and number of employees at the start of the year on the vertical. Bubble size represents number of job applicants.

    There were 7.6 million applicants to Starbucks last year. That's insane.

    [Nicolas Rapp]

  • Optimized dart throwing and other games

    January 17, 2012  |  Statistical Visualization

    Dart throwing heatmap

    If you play darts just trying to hit the bullseye, you aren't playing for maximum output. Don't fret though. DataGenetics is here to help with mathematical advice on how to play the game based on your skill level (Update: This is very similar to the dart work by Ryan Tibshirani, et al.):

    The optimal strategy for aiming depends on your skill as darts player. A very skillful player should aim for the middle of the triple 20; Much of the time he will hit his target, and the times he misses will be few enough that his average score will still be high.

    A very poor player should aim close to the bullseye, as just hitting the board will be an achievement (and a scoring one at that!). Aiming for the center maximizes the chances of hitting something.

    But what happens between these two extreme?

    I was a kid the last time I threw darts, and I was more interested in throwing them as high as I could in the air watching them stick into the grass. Maybe it's time to try it the right way.

    See also optimal gameplay for Battleship, Risk, and Candyland.

    [DataGenetics via infosthetics]

  • Apollo 11 lunar landing told through data

    January 4, 2012  |  Statistical Visualization

    From Yanni Loukissas of the MIT Laboratory for Automation, Robotics, and Society, comes the story of the Apollo 11 lunar landing told via multiple time series running in parallel and the back and forth between astronauts and mission control.

    The Apollo 11 visualization draws together social and technical data from the 1969 moon landing in a dynamic 2D graphic. The horizontal axis is an interactive timeline. The vertical axis is divided into several sections, each corresponding to a data source. At the top, commentators are present in narratives from Digital Apollo and NASA technical debriefings. Just below are the members of ground control. The middle section is a log-scale graph stretching from Earth (~10E9 ft. away) to the Moon. Utterances from the landing CAPCOM, Duke, the command module pilot, Collins, the mission commander, Armstrong, and the lunar module pilot, Aldrin, are plotted on this graph.

    Climax hits around the 4-minute mark. Too bad it doesn't get to the one small step for man part.

  • Corruption versus human development

    December 9, 2011  |  Statistical Visualization

    Corruption vs human development

    Transparency International released annual data for the Corruption Perceptions Index. The Economist plotted it against the UN's Human Development Index:

    Comparing the corruption index with the UN's Human Development Index (a measure combining health, wealth and education), demonstrates an interesting connection. When the corruption index is between approximately 2.0 and 4.0 there appears to be little relationship with the human development index, but as it rises beyond 4.0 a stronger connection can be seen. Outliers include small but well-run poorer countries such as Bhutan and Cape Verde, while Greece and Italy stand out among the richer countries.

    Interesting, although I suspect that the indices have some factors in common.

    [The Economist via @mikeloukides]

  • 40 years of boxplots

    December 6, 2011  |  Statistical Visualization

    40 years of boxplots

    Famed statistician John Tukey created the boxplot in 1970. It shows a distribution summary in a small amount of space. Hadley Wickham and Lisa Stryjewski look back on the old standby and its evolution up to present. Keep it in mind, while still used today, the boxplot was created with pencil and paper.

    One of the original constraints on the boxplot was that it was designed to be computed and drawn by hand. As every statistician now has a computer on their desk, this constraint can be relaxed, allowing variations of the boxplot that are substantially more complex. These variations attempt to display more information about the distribution, maintaing the compact size of the boxplot, but bringing in the richer distributional summary of the histogram or density plot. These plots can overcome problems in the original such as the failure to display multi-modality, or the excessive number of "outliers" when n is large.

    Alright, computers are useful. I guess.

    [40 years of boxplots]

  • Kill Math makes math more meaningful

    October 5, 2011  |  Statistical Visualization

    Kill Math

    After a certain point in math education, like some time during high school, the relevance of the concepts to the everyday and the real world seem to fade. However, in many ways, math lets you describe real life better than you can with just words. Designer Bret Victor hopes to make the abstract and conceptual to real and concrete with Kill Math.
    Continue Reading

  • The Fortune 500, 1955 to 2010

    September 28, 2011  |  Statistical Visualization

    The Fortune 500 Profits

    Since 1955, Fortune Magazine has published a list of America's 500 largest companies. What companies have risen to the top? Which ones have fallen? Ben Fry, of Fathom Information Design, visualizes the companies of past and present and how their rankings, revenue, and profit have changed.
    Continue Reading

  • Last.fm scrobbles as calendar heat map

    September 13, 2011  |  Statistical Visualization


    Martin Dittus, a former Last.fm employee, grabbed listening data for staff, moderators, and alumni, and visualized 8.7 million scrobbles in an extended calendar format.
    Continue Reading

  • Girl Scout cookie pie chart

    September 9, 2011  |  Statistical Visualization

    Girl scout cookies

    With Girl Scout cookie season around the corner, Wired pies it up with cookies showing percentage of sales. It's all about the Caramel deLites. [Thanks, Elise]

  • How the deficit got so big

    July 26, 2011  |  Statistical Visualization

    How the deficit got this big

    The US continues to rack up more and more debt, with a deficit in the trillions. But how did we get here? Teresa Tritch for The New York Times examines:

    In 2001, President George W. Bush inherited a surplus, with projections by the Congressional Budget Office for ever-increasing surpluses, assuming continuation of the good economy and President Bill Clinton’s policies. But every year starting in 2002, the budget fell into deficit. In January 2009, just before President Obama took office, the budget office projected a $1.2 trillion deficit for 2009 and deficits in subsequent years, based on continuing Mr. Bush’s policies and the effects of recession. Mr. Obama’s policies in 2009 and 2010, including the stimulus package, added to the deficits in those years but are largely temporary.

    Predicting the future is a tricky game. Even if you do have Grays Sports Almanac.

    [New York Times via Waxy]

  • All the countries that the US owes money to

    July 22, 2011  |  Statistical Visualization

    National debt

    In May 2011, the United States owned $14.3 trillion in debt. A lot of that is money is owed to other countries. Heather Billings and Todd Lindeman of The Washington Post break foreign debt down by continent and then by country.
    Continue Reading

Copyright © 2007-2014 FlowingData. All rights reserved. Hosted by Linode.