The Home for Wayward Statisticians

I've been noticing quite a few SmartCars on the road recently, and mentioned to my wife that I was curious about their safety and handling (San Antonio is currently one giant construction site, overrun with cracked pavement and orange barrels).  Looks like they're pretty good in the safety department, and the comment at the end hints that handling is OK, too.

Tip from the Instpundit.

Glenn Reynolds said it best: "When the people who say it's a crisis begin to act like it's a crisis, then I'll start to believe it's a crisis."  Carbon footprint, my a$$.

Update (14 May).  "Horrified!"

The City of San Francisco has figured out how to cut themselves in on a piece of the panhandling action: homeless meters.  Their motto: Be a part of change.  Don't give change.  If these are the people we've been waiting for, hold on to your wallets (and begging bowls).

Tip from Michelle Malkin.

This guy has perfectly nailed or current screwed up intellectual and educational landscape:

Such a partition of thinking from doing has bequeathed us the dichotomy of “white collar” versus “blue collar,” corresponding to mental versus manual. These seem to be the categories that inform the educational landscape even now, and this entails two big errors. First, it assumes that all blue collar work is as mindless as assembly line work, and second, that white collar work is still recognizably mental in character. Yet there is evidence to suggest that the new frontier of capitalism lies in doing to office work what was previously done to factory work: draining it of its cognitive elements.

Crawford blows the whistle on the Education Mafia's myth that everyone will have a wonderful, creative job once they get a college degree:

Much of the “jobs of the future” rhetoric surrounding the eagerness to end shop class and get every warm body into college, thence into a cubicle, implicitly assumes that we are heading to a “post-industrial” economy in which everyone will deal only in abstractions. Yet trafficking in abstractions is not the same as thinking. White collar professions, too, are subject to routinization and degradation, proceeding by the same process as befell manual fabrication a hundred years ago: the cognitive elements of the job are appropriated from professionals, instantiated in a system or process, and then handed back to a new class of workers—clerks—who replace the professionals. If genuine knowledge work is not growing but actually shrinking, because it is coming to be concentrated in an ever-smaller elite, this has implications for the vocational advice that students ought to receive.

...and he has some great advice

So what advice should one give to a young person? By all means, go to college. In fact, approach college in the spirit of craftsmanship, going deep into liberal arts and sciences. In the summers, learn a manual trade. You’re likely to be less damaged, and quite possibly better paid, as an independent tradesman than as a cubicle-dwelling tender of information systems. To heed such advice would require a certain contrarian streak, as it entails rejecting a life course mapped out by others as obligatory and inevitable.

Tip from The Corner (in a discussion that started with this)

Update (14 May).  The discussion widens to community colleges and developmental education over at Joanne Jacobs.  Follow the links.

Update (14 May).  The article that has everyone up in arms this week, Professor X's In the Basement of the Ivory Tower, is now on the web.  Thanks for the (somewhat irate) tip from Winds of Change.  I'm sympathetic with Professor X, but I'm not really on board with his approach.  I suspect his article is more an expression of frustration than anything else; X is running as fast as he can to keep the Wheel turning, when he really knows he should get off. It's pretty obvious that many people and our current college system are a disastrous mismatch; thousands of students are dropping out or flunking out with nothing to show for their time but a pile of debt.  I'd like to think that our colleges see these students as more than just a source of income, but I see a lot of broken eggs and damn few omelettes.  Real soon now, we need to step back, take a deep breath, and sort out how to educate those people who, today, are "not cut out for college."

I just received this very flattering email

I GOT YOUR INFORMATION IN A PROFESSIONAL DATABASE WHEN I WAS SEARCHING THROUGH INTERNET FOR A RELIABLE, HONEST AND TRUSTWORTHY PERSON TO ENTRUST THIS BUSINESS WITH. I WAS SIMPLY INSPIRED AND MOTIVATED TO PICK YOUR CONTACT FROM THE MANY NAMES IN THE LIST OF THE DIRECTORY. 
AFTER MY VIEW ON YOUR PROFILE, I WAS VERY MUCH SATISFIED AND DECIDED TO CONTACT YOU IMMEDIATELY FOR THIS MUTUAL BUSINESS RELATIONSHIP.

from a Mr.Andrew Amponsah, Former Accountant of the Ministry of Foreign Affairs, Ghana, who appears to be hopelessly corrupt.  He has offered to include me in a scheme to misappropriate some $17 million from banks in Ghana, but I must act now!  Why would I trust someone so obviously bent?

I'd appreciate the complement, if Mr Amponsah didn't think I was so susceptible to temptation.

Some recent research suggests that teaching math with concrete examples only muddies the waters:

...many educators in recent years have incorporated more and more examples from the real world to teach abstract concepts. The idea is that making math more relevant makes it easier to learn.That idea may be wrong, if researchers at Ohio State University are correct. An experiment by the researchers suggests that it might be better to let the apples, oranges and locomotives stay in the real world and, in the classroom, to focus on abstract equations...

This presents a problem for statisticians, since we maintain a tight link between the theoretical and applied parts of our discipline.  This result certainly helps to explain a phenomenon that has heretofore puzzled me:  many of the math majors who take my courses do fine on the theory problems, but struggle with data organization, programming, and other applied statistics problems.

...after reading this brilliant summation:

We in Denmark cannot figure out why you are even bothering to hold an election.

On one side, you have a b*tch who is a lawyer, married to a lawyer, and a lawyer who is married to a b*tch who is a lawyer.

On the other side, you have a true war hero married to a woman with a huge chest who owns a beer distributorship. Is there a contest here?

Shamelessly appropriated from American Digest, along with a relevant cartoon.

...comes from Wretchard at The Belmont Club: "...part of the attraction of the cult of celebrity is that it allows us to delegate the formation of our opinions to others." 

What a wonderfully concise summation of why I've never wanted to be one of the Kool Kidz.

Robert Kosara has an excellent introductory tutorial on treemaps over at EagerEyes.org.  Check it out.

FINALLY, that Blood For Oil thing just might kick in.  And guess who's responsible?

Tip from the Drudge Report.

Who says stats geeks don't have a sense of humor?  Check these out at Flowing Data.

Seen at Eduwonkette: "You know you're in trouble when the number of authors on the paper exceeds the sample size."

Tip from Joanne Jacobs.

Since the folks at Stuff White People Like haven't gotten around to it yet, let me mock stuff that chavs, hipsters, bobos, and wannabees like.  Today I pick trick names, like Moon Unit, Keanu, and Zeta-Jones.  Trick names are tricky; you want one to sound hip and distinctive, without instantly identifying you or your child as one of those people (avoid Lurleen, Lakeisha, and Bubba).  Double points for picking something like "Sean," to smoke out imitators who will tragically spell their newborn's name "Shaun" or "Shawn" or "Shahn."  Track the popularity of your favorite trick name here.

And Geoffrey Pullum has a great post over at Language Log in recognition.  He briefly (and correctly) touches on my pet peeve, the careless substitution of the word that for the word who, as in "I'd like to meet the person that painted this picture."  That is for objects or animals, who is for people.  Folks who pride themselves on being sensitive and considerate blithely reduce their fellows to the status of pets or furniture every time they speak.  How rude.

Mark Liberman has an outstanding article about the recent meta-analysis of anti-depressant effectiveness over at Language Log.  Not only does he use clear and succinct language to explain what's going on, he has some simple and effective graphics to back it all up.  Check it out.

Update (2 March).  Liberman is on a roll.  In his latest post, he takes on the rationalizations for separate-sex classrooms by looking at some of the statistically specious arguments provided.  Along the way, he gives a wonderfully concise explanation of the meaning of standard deviation:

Sax initially built his argument that girls hear better than boys on two papers published in 1959 and 1963 by a psychologist named John Corso. Mark Liberman, a linguistics professor at the University of Pennsylvania, has spent a fair amount of energy examining the original research behind Sax's claims. In Corso's 1959 study, for example, Corso didn't look at children; he looked at adults. And he found only between one-quarter and one-half of a standard deviation in male and female hearing thresholds. What this means, Liberman says, is that if you choose a man and a woman at random, the chances are about 6 in 10 that the woman's hearing will be more sensitive and about 4 in 10 that the man's hearing will be more sensitive.

From what I've read about separate-sex classroms, they do have their advocates and advantages, but things like student hearing and brain volumes aren't the criteria.  My thanks to Mark Liberman for reminding me of this probability interpretation; I need to use it in my classes more often.

What is this, Hissy Fit Week?

Now some thumbsucker in Blighty is giving himself the vapours, worrying about killer robots.  When the robos start doing drive-bys, or preaching jihad to one another, I'll start worrying.  Until then Professor, spend a little less time watching the SciFi channel, and a bit more time out of doors, getting some exercise.

Tip from the Instapundit.

Update (28 Feb).  A bit more balanced view here. Tip from the Geek Press.

...and Arnold Zwicky over at Language Log is having the vapors about it.  How can he take an organization acronymed as SPOGG seriously? 

I'd be happy if my students were able to match pronouns to antecedents, avoid singular verbs with plural subjects, and write a paragraph in something other than the present tense.  Proactively renormalizing their lexical diversity to something regular folks say would help, too. (My tip:  try not to sound like a motivational speaker or a criminal defense attorney; people will think you're a grifter.)  Meanwhile, read Eats Shoots and Leaves and do your curmudgeonly best to stamp out the inappropriate wild apostrophe--it's your grammarly duty.

Time for a little critical thinking about global warming.  First, read Park's Seven Warning Signs of Bogus Science; then see Briggs tackle the question "Is climatology pseudoscience?" 

Tips from Muck and Mystery and American Digest.

Update (25 Feb).  Looks like this global warming thing isn't working out so good for the Chinese or the Canucks.  Tip from the Drudge Report.

...from everyone but the Archbishop.  He didn't call her a Friend of Babykillers, nor did he threaten to excommunicate the entire faculty and staff of St Mary's University, but from an Archbishop, this is a strong hint. 

I love the closing line " Politicians who have appeared on the St. Mary's campus include Ronald Reagan, H. Ross Perot and Kinky Friedman."  A US President and two grandstanders who were never elected dogcatcher--I never knew "politician" was such an all-encompassing group.  Hell, maybe I'm a politician!

I've been reading the Freakonomics blog since it started; they have some interesting stuff.  To make sure I stayed current, I subscribed to the blog with Bloglines.  BUT...after reading the comments on this post, I've decided that I want nothing to do with the kind of people who read that blog.  Whatever it is they've got, I don't want it jumping off them onto me.  (I wonder if the entire NY Times readership is infested.) As of now, they're unsubscribed.

Update (7 February).  Lileks expresses his dismay in a wonderful extended snark, and an anonymous commenter gives me a gentle, but bracing, whack on the side of the head.

...the more his ass shows.  I just received this in my email:

Math technology produces amazing results in the classroom! To get the attention of his students, applied mathematician Tim Chartier set out to explain the mathematical processes behind digitizing and animating the Star Wars character Yoda. Yoda first appeared in the Star Wars saga in the 1980 film The Empire Strikes Back. Yoda was represented by a puppet in the original film but more recently, the character was produced by computer animation, employing mathematical concepts from such areas as linear algebra, calculus, differential equations, and numerical analysis.   The application “Maple Adds an ‘Out of This World’ Touch to Math Learning” demonstrates the processes of digitizing and animating a 3D image of Yoda using mathematics. To see other applications, visit the Maplesoft Application Center and choose from over 1,500 applications and tutorials from a variety of disciplines. Professor Chartier is passionate about finding relevant, exciting examples that he can use to engage his students. "I want to show students how math can be applied in many interesting areas of our lives," said Chartier. By using mathematical technology to illustrate examples of real math applications he has enabled students to better understand not just how to do math, but why they should want to.   Read the user case study “Mathematical software used to digitize Star Wars character Yoda” to learn more. Kind regards, Mark Anderson Maplesoft 1-800-267-6583 ext. 421 © 2008 Maplesoft, a division of Waterloo Maple, Inc., 615 Kumpf Drive, Waterloo, ON, Canada, N2V1K8. Maple and Maplesoft are trademarks of Waterloo Maple Inc. You are receiving this commercial email in an effort to keep you abreast of the latest developments at Maplesoft. To manage subscriptions or to opt out of all commercial email communications from Maplesoft, please click here. To view our privacy policy, click here.

So let me get this straight.  When the Star Wars films were full of fresh ideas, surprises, and mystery, Yoda was a puppet.  Then later, when the films became tired reruns that were no more than giant toy commercials that blew chunks, Yoda was a computer animation, and MapleSoft helped. Thank you so much, Mr Anderson, for fingering your own employer as an Enemy of the People's Aesthetic Sensibilities, you wanker.  I'd also suggest that Professor Chartier be sentenced to 40 hours of mandatory critical cinema courses before being allowed to teach another math course.  Just another argument in favor of Mathematica over Maple.

One of my several innovations this semester in the Applied Statistics course is the incorporation of a significant writing component.  The statistics faculty has long complained about students producing ghastly, unreadable project reports, but they seem to treat it as some sort of natural phenomenon, like the weather.  Since Applied Statistics is the first upper-division statistics course required of statistics, actuarial science, and mathematics majors, the department chair and I decided this was the ideal place to start teaching scientific writing.  Hence, the significant writing component.

The driver for adding this, this semester, is a campus-wide initiative in writing across the curriculum, supported by our Writing Program, which has the clout of a large department at UTSA.  The support is more than just handouts and lip service:  I actually have a W.P. faculty member assigned to serve as the Writing Consultant to my course to help me design assignments and course materials.  He's even going to give some short lectures!  (He and I both subscribe to the Conspiracy Theory of Bad Scientific Writing: students in the sciences and engineering consciously avoid enrolling in any courses with obvious writing requirements.)

This is all background to the first writing assignment, coming up 31 January:  write a resume and cover letter for an application to a summer internship with the U.S. Census Bureau (there are such things, available to my students).  Sure,  it's not statistical presentation, but it's a good warm-up to get the students writing.  After all, they can't claim they don't know the subject!

Here are two videos I'm going to make available to my students to help them along:  resume writing and the cover letter.  Thanks to James Hudnall for pointing them out.

Update (7 February).  Read about "short attention spaniels" and Cover Letters From Hell in the Killian Advertisting Newsletter.  Tip from Joanne Jacobs.

Update (14 May).  One of my students landed the internship!  I think I deserve at least a B.

The CDC reports that the overall occurence of HIV in the US is about one-half of one percent, depending on risk group, of course.  Combine these numbers with the published sensitivity and specificity of the fast HIV test, and you've got a great lecture on Bayes' Theorem.

Tip from the Drudge Report.

Update (30 January).  Changed the FDA link for sensitivity and specificity, since the old link reported specificity as 100%, which is ludicrous.

Van Der Leun gives us 27 Daily Affirmations for Bloggers.  My favorite:

Joan of Arc heard voices too, but she was wise enough to have herself set on fire before she logged on.

He has one about blockquotes, too.

Yesterday was the first meeting of UTSA's Statistical Consulting class, and the instructor, Dr Stephanie Cano, had plenty of projects--with anxious clients attached--to assign.  Since I'm her sidekick in the university's Statistical Consulting Center, I had the pleasure of presenting two of the project statements to the class, since I conducted the initial interviews with the clients.  Interesting stuff:  Family Influences on Study Abroad Participation among Hispanic Undergraduates, and Linguistic Prestige (Spanish vs English) in the Philippines.  I'm interested to see how these turn out.

Bloglines kicked up a very timely posting of Rules for Statistical Consulting, presented in a mini-symposium at Columbia University.  Tip from Andrew Gelman.