Statisticians apply stylometry to identify authors and they invent algorithms that assess essays
Posted by mark in pop, Uncategorized on June 20, 2012
My colleague Tryg, who, like me, loves word play, drew my attention to this podcast* that explains how “By Their Words You Shall Know Them.” I teed it up on my smart phone and listened on my way to work yesterday—a fun way to pass my half hour commute into Minneapolis from my home in Stillwater, Minnesota. One thing that caught my ear was the early 1960s work by Harvard statistician Frederick Mosteller to pin down who wrote 12 of the 85 Federalist papers published under the pen name “Publius”. He and colleague David Wallace (University of Chicago) applied Bayes; theorem to attribute these writings to James Madison (as opposed to Alexander Hamilton). Mosteller also led the way to today’s reliance on statistics in sports by doing the first known academic analysis of baseball in 1946—concluding that luck rules even in a seven game World Series. He didn’t agree that, though the Cardinals beat his home town Red Sox, the best team actually won.
This analytical dissection of written words has come to be known as “stylometry”. As computing power increases and algorithms develop, writings are being put to the test. For example, see this New York Times Digital Domain column from earlier this month that details developments in ‘essay-scoring engines’. For now the students hold the upper hand on computer-based grading of papers—web-based essay mills can easily throw together fact-laden gibberish that fools the virtual professors. These are easily seen by teachers when they skim the results—check out some goofy passages passed along by Duke University professor Dan Ariely in this editorial for the Los Angeles Times .
The advent of spell-checking and grammar inspection in word processors has been a boon for writers. However, passing these tests does not necessarily lead to clear prose. When I started work as an engineer, the head of our process development group handed me a little booklet by Robert Gunning on “How to Take the Fog Out of Writing”. He advocated short, active sentences—not the passive, long and pedantic style I’d grown accustomed to from academia. See how your writing scores for fog using this online tool by Simon Bond. The quote below scored 20.86. This paragraph came back with a fog index of 9.152 (up to this clause to be precise!). Gunning’s score estimates the years of formal education needed to understand text on a first reading. Thus my writing supposedly can be understood by 10th grader. Draw your own conclusions on the readability of our founding fathers.
“As there is a degree of depravity in mankind which requires a certain degree of circumspection and distrust, so there are other qualities in human nature which justify a certain portion of esteem and confidence.”
– Madison, Federalist Papers #55, 346
*By online Slate magazine’s Lexicon Valley host Mike Vuolo
Irish Times says “serious issue settled” — Guinness does indeed travel badly
Posted by mark in Consumer behavior, Uncategorized on June 9, 2012
Lab Times author Thirsty O’Leary provides this summary of a scientific study by Liam Glynn, et al, that proves Guinness beer does not travel well. Some say it’s a conspiracy of the Irish—them drawing off the cream from the barrel. Although Guinness is not my cup of tea, I admire the work that went into this experiment. These zealots for zymurgy went all out! And, as those of use students ; ) of stats know, Guinness goes down well with quantitative research of this sort.*
“Each pint is like a child. You have to mind it through the entire process.”
— Fergal Murray, Guinness brew master
*See Guinnessometrics: Saving Science and Statistics With Beer
Brain drizzling? Try linking instead.
Posted by mark in science, Uncategorized on May 13, 2012
Early on in my career as a chemical engineer working in R&D process development I came to the realization that many good ideas get shot down prematurely. Granted, many of these thoughts come out half baked, but in the proper environment they can lead to some very nourishing developments.
I always thought Osborn’s methods for brainstorming counteracted the quenching of creativity. However, although his approach certainly does generate a quantity of ideas, the end results never proved nearly as astounding as one might expect.
Earlier this year The New Yorker magazine debunked as Groupthink many of Osborn’s cherished tenets, such as allowing no criticism. The current thinking is that you gather a diverse group of bright people and then just let things fly with no holds barred. The fear of public humiliation forces the participants to think a bit before speaking. If they do get strong criticism, these creative people must regroup their thoughts and try again. The best idea(s) tend to win out.
Here is one minor variation on the “no rules” creativity session that I suggest: Ask that everyone come in with one idea to throw into the pot. Then let the fun begin!
Given Osborn’s rules are passé, where should you turn to next for catalyzing creativity? I recommend you consider Idea-Links. I have had the pleasure of picking the brain of the author, Jim Link—a very energizing fellow. Believe me, he really knows how to get people to think outside of the box.
“To raise new questions, new possibilities, to regard old problems from a new angle, requires creative imagination and marks real advance in science.”
– Albert Einstein
If you have other ideas on fostering creativity (or wish to criticize those already proposed), toss them into the ring. Do not be shy (nor sensitive).
Ivory towers of academia (& shiny ones in Vancouver)
Today’s Vancouver Sun suggests that a competitive university culture discourages sharing of knowledge, which then leads to the publication of many flawed and fraudulent studies. This is a rehash of issues I cited recently with the warning Beware of obvious answers and positive results. It would be great, albeit a bit boring, if journals published negative results from well-designed experiments with adequate power to see beneficial results. As my colleague Wayne Adams says
“Most of what you learn from an experiment is what NOT to do.”
PS. I took this picture Granville Island looking across to downtown Vancouver.
“Randomistas” building steam for government to do better by designed experiments
“Businesses conduct hundreds of thousands of randomized trials each year. Pharmaceutical companies conduct thousands more. But government? Hardly any.”
–David Brooks, The New York Times, 4/26/12 editorial seen here
For those of us in the know about statistical tools this statement provides light at the end of a long tunnel. However, this columnist gets a bit carried away by the idea that an FDA-like agency inject controlled experiments throughout government.
Although it’s great to see such enthusiasm for proactive studies based on sound statistical principles, I prefer the lower-profile approaches documented by Boston Globe Op-Ed writer Gareth Cook in this May 2011 column. He cites a number of examples where rigorous experiments solved social problems, albeit by baby steps. Included in his cases are “aggressively particular” successes by a group of MIT economists who are known as the “randomistas”—a play on their application of randomized controlled trials.
Evidently the obvious success of Google (12,000 randomized experiments in 2009, according to Brooks) and others reaching out over the internet has caught the attention of the mass media. Provided they don’t promote randomistas running wild, some good will come of this, I feel sure.
Where the radix point becomes a comma
Posted by mark in Basic stats & math on April 23, 2012
Prompted by an ever-growing flow of statistical questions from overseas, Stat-Ease Consultant Wayne Adams, recently circulated this Wikipedia link that provides a breakdown on countries using a decimal point versus a comma for the radix point—the separator of the integer part from the fractional side of a number.
For more background on decimal styles over time and place see this Science Editor article by Amelia Williamson. It credits Scottish mathematician John Napier* for being the first to use a period. However, it seems that he wavered later by using a comma, thus setting the stage for this being an alternative. Given the use of commas to separate thousands from millions and millions from billions and so on, numbers can be misinterpreted by several orders of magnitude very easily if you do not keep a sharp eye on the source.
So, all you math & stats boffins—watch it!
*As detailed in this 2009 blog I first learned of this fellow from seeing his bones on display at IBM’s Watson Research Center in New York.
Marshmallows measure the speed of light (and get put to other good uses)
One of my favorite blogs, Flowing Data, provided me the heads-up on a great lecture by Adam Savage (the Mythbuster’s guy) called “Simple ideas lead to scientific discoveries”. I really enjoyed all of his stories, but especially the one on Hippolyte Fizeau’s measurement of the speed of light in 1849. Ingenious!
Coincidentally, my brother Paul forwarded me a detailing of how one can measure the speed of light with a tray of mini-marshmallows! Check it out at this Science Blog written by theoretical astrophysicist Ethan Siegel. This sharp-fingered fellow (if you view his blog you will see what I mean) goes on to tout a marshmallow-made diorama that ‘peeps’ recent claims of particles going faster than the speed of light.
That leads me to puffing up my daughter Emily, who achieved the “peeple’s choice” award in the Saint Paul Pioneer Press Ninth Annual Marshmallow Peeps Diorama Contest. She and two of her closest peeps produced The Mupeeps Take Minnepeepolis. It looks very much like the view out of my window from Stat-Ease headquarters east of downtown Minneapolis.
By the way, my favorite Muppets are Bunsen and Beaker. See them demo their invention of fireproof paper here. At the Muppets Lab one should always be prepared with fresh marshmallows on a stick. I advise going for two at a time. o——<8
High rollers beat the lottery odds
Posted by mark in Consumer behavior on April 2, 2012
The $640 million jackpot in the Mega Millions lottery Friday night created a huge buzz. Unfortunately this fizzled out for all but the three big winners in Illinois, Kansas, and Maryland. Even we analytical types get swept up in the frenzy, seeing as how the money sunk in prior drawings brings the expected value over 100 percent. Yes, the odds of 1 in 176,000,000 remain daunting, but it sure is fun to have a few numbers to play with.
The really gutsy lottery wonks focus on other games where situations arise that make huge bets nearly a sure thing. For example, see this Boston Globe heads-up on “a game with a windfall for a knowing few”. Imagine showing up at your corner gas station with $100,000s in cash for lottery tickets—that would be a great day for the own, especially given the seller earns a commission that can grow to $100,000 for some jackpots.
“Bettors like the Selbees, who spent at least $500,000 on the game, had almost no risk of losing money.”
– Mark Kon, a professor of math and statistics at Boston University
Holing up on a frozen Minnesota lake
The March issue of Minnesota Business magazine, a valuable source of information and insight for growing companies,* provided a fascinating statistic, hard to believe really: 25,000—the number of ice fishing holes drilled last month for an ice-fishing contest on Gull Lake. Minnesota-based StikeMaster Corporation provided the augers. See their video for a demonstration.
Meanwhile (reported on page 44), elsewhere on Gull Lake (far from the 25,000 holes, I hope), Grand View Lodge offered the ideal meeting place for getting away from the office. See this report from our local CBS television affiliate—you will be amazed.
Sadly it seems that spring is nearly sprung so we must now endure 6 months of warm weather before the fun can begin again.
*Full disclosure: My daughter Emily is Graphic Designer for the production of this publication by Tiger Oak Media of Minneapolis.
Beware of obvious answers and positive results
Posted by mark in science, Uncategorized on March 4, 2012
“Most results, including those that appear in top-flight peer-reviewed journals, can’t be reproduced.”
This is a “dirty secret” revealed by the Wall Street Journal’s Gautam Naik in this December report. It cites statistics from Bayer that nearly two-thirds of published studies could not be replicated. Naik blames the complicated nature of experiments nowadays along with the “positive bias” researchers driven to produce results. Glenn Begley, vice president of research at Amgen, a biotechnology company, suggests that “academic scientists, like drug companies, should perform more experiments in a ‘blinded” manner to reduce any bias toward positive findings.”
Meanwhile, Duncan Watts, author of Everything is Obvious: *Once You Know the Answer says
“When you do the experiment properly [randomized and controlled], all the numbers go down.”
He’s speaking on the bias of marketing executives toward their own sensibilities, which often do not reflect those of the population being sold to. See what the Financial Times “undercover economist” Tim Harford says about this here. Unfortunately, in my experience, those (the analysts) who know better than to extrapolate from small, non-representative sample of opinions from the ‘powers-that-be’ (often n=1, that is—the Boss) get very little support for spending money to put these assertions to the test. Even though you know the top dogs might be barking up the wrong tree it’s easiest just to go along with the pack and press ahead. To do otherwise risks suffering a painful bite-back. Yes, I am a cynic.