Charlie Park has a nice post describing Tufte’s slopegraphs (old chart, new name).
Kaiser Fung likes these a lot; he’s been calling them Bump charts.
I introduce these to my undergrads when we discuss the paired t test.
Tip from kottke.org.
Update (16 July). James Kierstead publishes an R implementation.
Posted in programming, statistical graphics, teaching
Back in grad school, whenever a statistical problem had us stumped, we would joke about having a bad case of dyscalcula, comparing ourselves to dyslexics because the problem was so puzzling we weren’t sure we understood the question, let alone had a clue about finding the answer. Well, dyscalcula is making its real-world debut.
Oh goody! another friggin’ made-up disability just begging for an army of thumbsuckers to cater to it. I can already see the Math Ed folks gearing up to teach college-level courses in counting your fingers. Right behind them come the Food Nazis, who’ll jump on this to explain that dyscalcula leads to obesity due to Poor Portion Perception. Then come the financial regulators, the traffic safety gang, the FDA, the FTC, the PTA, etc. etc. This will be a research (and comedy) goldmine.
Dollars to donuts (that’s 2:1 for you dyscalcics), most of these poor performers catch on just fine if their baby sister tries to short them on the split of the Halloween candy or a piece of cake.
Posted in 1984, bullshit, dumb ideas, teaching, word of the day
Briggsy gives a dead-simple explanation for spotting and profiting from a Dutch Book set of odds. Even an undergrad can do it!
Posted in good stuff, math and statistics puzzles, money, teaching
On his Forbes blog, Jerry Bowyer espies an Internet iceberg dead ahead of Titanic U.
…you and your iPod (or desktop) can listen to the smartest people in the world give interesting lectures on the most important topics for free, or you can pay lots of money to hear an inarticulate and resentful grad student ladle out early 1960s French intellectual fads in one of collegedom’s cavernous freshman lecture halls at a time of his, not your, convenience.
If we–university faculty–expect students to keep showing up, we’d better start giving value for their time and money. Snoozeworthy lectures, 2.0 GPAs, and no marketable skills ain’t gonna cut it.
The Amazing Khan does it again with his suggestion to do lectures OUTSIDE class, and “homework” IN class. The guy’s a madman. A wonderful, gifted madman.
Update (28 March). This must be a big deal inedeed if even cow grazier Gary Jones gets intrigued.
Posted in amazing folks, good stuff, teaching, Technology
Frank Fleming thinks our education system is on the wrong track:
Children are taught for 13 years in grade school, and many people want everyone to get at least 4 years of college on top of that. And what exactly do we get out of all this? If someone told me I was going to spend the next 17 years just studying, I’d expect at the end of it all to be Batman — a master of all sciences, languages, and martial arts. We’re lucky if our kids come out of this able to read and with at least one marketable skill.
I need to check Frank’s statistics on teachers and students. 76 million students and 7.2 million teachers. That’s not even an 11:1 ratio, so why all the fuss about budget cuts pushing schools to have classes with 30 or 40 students?
Posted in Higher education, humor, teaching
Undergraduate assessment is about to get a lot more attention. I’m looking for more outside assessments like the Actuarial Exams and the SAS certificates.
Posted in Higher education, teaching
I’d like to make a fair and random choice among 3 alternatives, but the only randomizing device I have available is a coin to toss. Worse yet, I suspect the coin may be biased. What to do?
Using data forensics to detect cheaters on standardized tests..is there anything statistics can’t do?
Posted in statistics, teaching, Technology
