hints of a fearsome truth

Shop­ping for text­books, I’ve stopped in at three book­stores on cam­pus. Just for fun. No, really — I always like to stroll up and down the aisles and get a feel for what all the peo­ple in all the var­i­ous col­leges and their depart­ments are assign­ing. Now and then I even pick up a neat-​​looking Machine Learn­ing, Mol­e­c­u­lar Dynam­ics, or His­tory of Sci­ence book. So sue me; I’m a pan-​​geek.

My wife was with me this last time. She pointed out, as she often does, some­thing I missed entirely. There are, like, sev­en­teen dif­fer­ent “Intro­duc­tion to Prob­a­bil­ity and Sta­tis­tics” text­books, scat­tered in the Biz School, Engi­neer­ing, Med­i­cine, Biol­ogy, Psy­chol­ogy, Social Sci­ences, Applied Math, and for all I know Art His­tory shelves [I did see Guns, Germs and Steel as an assigned read­ing in one very inter­est­ing Art His­tory class].

Many of these are, by impli­ca­tion, reme­dial Prob­a­bil­ity and Sta­tis­tics — for grad­u­ate stu­dents, in many cases, but also for “advanced” under­grad­u­ates. And that is so wrong, it hurts. Prac­ti­cal, mod­ern prob­a­bil­ity and sta­tis­tics courses should be required at the entry level in all cur­ric­ula. Period. I say quit futz­ing with cal­cu­lus for any­body but math­e­mat­ics majors, and get every­body tight with R.

Oh, and as I recall there was not one Prob­a­bil­ity and Stats books in the Ele­men­tary Edu­ca­tion shelves.

This entry was posted in Uncategorized by Tozier. Bookmark the permalink.

9 thoughts on “hints of a fearsome truth

  1. I con­fess: I _​should_​ have redesigned the intro­duc­tory prob­a­bil­ity and sta­tis­tics class I’m teach­ing, so it uses R and not (may Heaven have mercy on me) Minitab. I should also have redesigned it so it’s more mod­ern, but I was a lit­tle con­strained by what the depart­ments I’m pro­vid­ing a ser­vice for expect the stu­dents to emerge know­ing. Still, I must enter a plea of “guilty, by rea­son of laziness”.

  2. Actu­ally, I was won­der­ing why they were all by dif­fer­ent authors (and of course, mostly all new edi­tions — but that’s a dif­fer­ent topic).

    But I also found it inter­est­ing that each depart­ment felt it nec­es­sary to pro­vide the class for *their* stu­dents. Hav­ing had basic P&S classes in engi­neer­ing and in busi­ness (sep­a­rated by 18 years), I can state with cer­tainty that the nor­mal dis­tri­b­u­tion didn’t change in that time, and nei­ther did the method of teach­ing it. [Well, except the first time was Minitab, and the sec­ond Excel (busi­ness, you know).] This seems to be one area where it makes sense to have a cen­tral­ized course, doesn’t it? Much like fresh­man chemistry.

    But then Cosma’d lose out on cre­at­ing a new class ;)

    By the way, Cosma, it’s not “lazi­ness,” it’s “explor­ing the land­scape as it is.”

  3. Heh. May Heaven have mercy on us all: Bar­bara and I both learned sta­tis­tics with Minitab. In the Old Days. When it was all there was.

    Not like Kids These Days. In our day, you Learned Sta­tis­tics, by gum, or onto the ice floes you went. And they beat us with sticks, too. Both ways uphill.

  4. Ah well, now you know sta­tis­tics you at least have some­thing that will help you make angry every­time num­bered are men­tioned in the papers or on TV.

  5. Argh! s/​numbered/​numbers/​

    Any­way, I came back because of Barbara’s ques­tion; I guess it is a sim­ple case of stak­ing a claim. If you can give Sta­tis­tics lec­tures in your own depart­ment, it means you can (sort of) jus­tify one more teach­ing posi­tion. There was a lot of that going on at my uni­ver­sity. At least I think there was; my sus­pi­cions were never acknowl­edged of course. (Me being a lazy news­man did not help either when it came to dig­ging up the truth.)

  6. Minitab is a great mul­ti­ple regres­sion pro­gram, accord­ing to my hus­band, but he’s just a nut for that kind of stuff. We still have a book some­where on it col­lect­ing dust in the attic.

    We just had a very inter­est­ing con­ver­sa­tion about whether you can truly ever teach prob­a­bil­ity and come away with defi­nate under­stand­ing, because that would indi­cate that prob­a­bil­ity doesn’t change over time. Which he says, prob­a­bil­ity is the same in any given instant. But I say, it can’t be. Oth­er­wise, wouldn’t a book on prob­a­bil­ity be as mod­ern today as it was 20 years ago? You’d only ever need one.

    And you wouldn’t believe the sen­tence I just back­spaced over. It started some­thing like, “The prob­a­bil­ity of prob­a­bil­ity never chang­ing is prob­a­bly…” Gah!

  7. Ok, what stats books would you rec­om­mend for some­one with an hon­ours degree in Pure Math­e­matcs and Com­puter Sci­ence and a rea­son­able amount of gen­eral stats picked up from broad gen­eral sci­ence read­ing?

    Ide­ally I’m look­ing for some­thing abstract enough to satisify the math­e­mati­cian in me, but with real case stud­ies appli­ca­tions to make moti­va­tion eas­ier. I’d like to under­stand epi­demi­ol­ogy papers, for exam­ple, (say the Lancet Iraqi deaths study) and be able to read the bits of Cosma’s PhD the­sis that went over my head when I looked at it…

  8. Danny: “A Guide to Econo­met­rics” by Peter Kennedy is your man. It is the only text­book worth shit on the subject.