I teach at a very academically rigorous school.
-
They know a little calc before they get into physics. And they often tell me about how they used it in my calc class.
But, what I wish we could do is stop treating Statistics like it's... the math class for "weak" students who couldn't do calculus.
Part of the problem is there is still a tendency to classify kids as "math people" and "not math people" although I'm breaking my peers of this notion every chance I get. Part of it is this snobbishness pure math people have about stats.
-
myrmepropagandistreplied to myrmepropagandist last edited by
And where has treating statistics like "the lesser math" gotten us? I blame the messy way LLMs and other tools are being slathered around on everything on the general neglect of statistics by "serious math people"
It's an unsupervised area and it has fallen into chaos. And they have the powerful tools that claim to do the magic that the people want.
-
Samuel Smith ✅replied to myrmepropagandist last edited by
@futurebird @whknott having taken both Calc and Stats, I'd say statistics was harder for me.
But then, I'm no mathematician. Math is a tool to accomplish a goal, not something to play with.I've met people with the opposite opinion, and that's fine. We just need to realize that those opposing philosophies can complement each other or fight each other. It's up to us to decide which it is.
-
@Jirikiha @futurebird @whknott I'm *far* from an expert in math / stats. I took 2 years of honours math as part of my looong ago comp sci degree, and have been generally interested in mathy stuff since.
My impression is that the math behind statistics (at least the foundations) is deep: measure theory, the Lebesgue integral, and other terms I recognize as topics, but do not have even a basic understanding of.
-
@DaleHagglund @Jirikiha @whknott
All that and combinatorics and probability too. It's exceedingly nontrivial. My graduate advisor said "in combinatorics the questions are all easy to understand and impossible to answer"
So then why is there is notion that statistics is for "lightweights" ? Part of it is all of the barebones rough and ready recipe based stats courses for business and social science majors... but there are calc classes like that too so why does it stick only to stats?
-
Really the "really basic stats courses" have done us all a huge disservice, as you point out.
My first statistics course was a 3xx course that required calculus and after that I went on to take several topics in advanced probability and statistics. It's _so so_ nontrivial and people think it is just like… plugging in this formula and trying to get at least 30 people in your sample or somesuch.
-
I actually struggled when tutoring someone in one of those stats courses that doesn't require calculus.
Because it was all rubrics and heuristics. Many of which I had not memorized or, if I ever had memorized them, had not retained them.
We've lost the essence of something important there.
-
Meanwhile everyone still graduates and doesn't seem to be ale to figure out these things (https://ics.uci.edu/~jutts/AmerStat2003.pdf), which to me are some of the core lessons I'd impart on people, even if the class has nothing to do with calculating per se. Who cares if you can calculate a t-test if you don't know when to apply it?
But things like understanding the difference between significance and effect size is huge and matters regardless.
It's challenging.
-
@hrefna @futurebird @DaleHagglund @Jirikiha @whknott
As a stats phd I just want to say I love you all, thank you for the validation. Really helps counter the person who when I told them I got into my program they said “what is there even to study?”
-
I view some of the work I have done with probability (and specifically stochastic modeling) to be some of the most challenging, difficult work of any mathematics I have studied.
Also some of my favorite, but there's just _so much_.
