Archive for August, 2010

Quantifying statements of confidence: Is anything “iron clad”?

Today’s “daily” emailed by The Scientist features a heads-up on “John Snow’s Grand Experiment of 1855” that his pioneering epidemiology on cholera may not be as “iron clad” as originally thought.  A commentator questions what “iron clad” means in statistical terms.

It seems to me that someone ought to develop a numerical confidence scale along these lines.  For example:

  • 100% Certain.
  • 99.9% Iron clad.
  • 99% Beyond a shadow of a doubt.
  • 95% Unequivocal.
  • 90% Definitive.
  • 80% Clear and convincing evidence.
  • 50% On the balance of probabilities.

There are many other words used to convey a level of confidence, such as: clear-cut, definitive, unambiguous, conclusive.  How do these differ in degree?

Of course much depends on how is making such a statement, many of whom are not always right, but never in doubt. ; )  I’m skeptical of any assertion, thus I follow the advice of famed statistician W. Edwards Deming:

“In God we trust, all others bring data.”

Statistics can be very helpful for stating any conclusion because it allows one to never have to say you are certain.  But are you sure enough to say it’s “iron clad” or what?


1 Comment

Blah, blah, blah…”quadratic”

This add by Target got my attention.  It reminded me of my futile attempt to get my oldest daughter interested in math.  For her the last straw was my overly-enthusiastic reaction to her questioning me why anyone would care about quadratic equations.  Perhaps I over-reacted and lectured on a bit too long about this being a very useful approximating function for response surface methods, blah, blah, blah…

No Comments

Opportunistic eating a problem for new college students

A study recently published online by the Journal of Adolescent Health concludes that female (but not male!) students in dorms with dining halls gained significantly more weight than those who were forced to go out to eat.  The lead author, Kandice Kapinos (University of Michigan), took advantage of the practice of colleges to randomly assign dorm rooms.  Specifically, she and her study team examined the weight gain of 388 freshmen at Marquette University.  (See a few more details in this press release.).However, they relied on self-reporting rather than direct observation and measurement, which creates some doubt about the validity of their conclusions.  After all, people have been known to fudge about their weight. 😉

Nevertheless, based on observation of three daughters and two sons who went off to college, I believe that Kapinos et al are really on to something.  This was sealed in my mind from the observation of my youngest girl, who soon will start her third year in a biochemistry program.  She said it really is very simple – the female students hang around the dorm dining hall for social reasons, during which times they naturally munch on stuff and pack on the pounds.  I think for the good of their students it would be wise of schools not to put cafeterias in the dorms.

“I think perhaps that women are a little more socially oriented at college, and one social thing they engage in might be, ‘Let’s go get a snack,’ Men may not tend to do that as much.”

— Wayne Westcott, Senior Fitness Executive for the YMCA in Quincy, Massachusetts

By the way, putting on weight after going away to college — the proverbial “freshman 15” – is bound to happen, I think; and for both men and women.  I gained 15 pounds after moving into a dorm at Michigan State University.  It had a dining hall in the building.  However, I’ll bet I’d have added weight just the same even if the meals were served elsewhere on campus.


No Comments