To do: Construct a build-your-own-relevant-statistics-class kit.

Alexis Lerner, who took a couple of our courses on applied regression and communicating data and statistics, designed a new course, “Jews: By the Numbers,” at the University of Toronto:

But what does it mean to work with data and statistics in a Jewish studies course? For Lerner, it means not only teaching her students to work with materials like survey results, codebooks, archives and data visualization, but also to understand the larger context of data. . . .

Lerner’s students are adamant that the quantification and measurement they performed on survivor testimonies did not depersonalize the stories they examined, a stereotype often used to criticize quantitative research methods.

“Once you learn the methods that go into statistical analysis, you understand how it’s not reductionist,” says Daria Mancino, a third-year student completing a double major in urban studies and the peace, conflict and justice program. “That’s really the overarching importance of this course for the social sciences or humanities: to show us why quantifying something isn’t necessarily reductionist.” . . .

Lerner hopes her students will leave her class with a critical eye for data and what goes into making it. Should survey questions be weighted, for example? How large of a sample size is large enough for results to be reliable? How do we know that survey respondents aren’t lying? How should we calculate margins of error?

Lerner’s students will leave the course with the tools to be critical analysts, meticulous researchers and – perhaps most importantly – thoughtful citizens in an information-heavy world.

This sounds great, and of course the same idea could be used to construct a statistics course based on any minority group. You could do it for other religious minorities or ethnic groups or states or countries or political movements or . . . just about anything.

So here’s what I want someone to do: Take this course, abstract it, and make it into a structure that could be expanded by others to fit their teaching needs. Wouldn’t it be great if there were hundreds of such classes, all over the world, wherever statistics is taught?

A build-your-own-relevant-statistics-class kit.

Let’s take Lerner’s course as a starting point, because we have it already, and from there abstract what is needed to create a structure that others can fill in.

Tomorrow’s post: Instead of replicating studies with problems, let’s replicate the good studies. (Consider replication as an honor, not an attack.)

7 thoughts on “To do: Construct a build-your-own-relevant-statistics-class kit.

  1. This does sound like a cool idea. In my ideal world (which I attempt imperfectly to realize), statistics education would be two-pronged:
    1) As in the focus of this course, one prong is focused on how quantitative reasoning can add meaning to a domain. In this case, it adds meaning to one’s understanding of society and history, but of course it adds meaning to many other domains as well, scientific obviously but also potentially other humanities topics like literature and music theory.
    2) The other prong is that domain-specific meaning is essential for useful quantitative reasoning. This is something that comes up quite frequently around here in various guises, namely, that statistics is not a mechanical exercise, but requires a lot of thought to understand the connections between measurement, modeling, and theory. These connections require an understanding of what the quantities being analyzed actually represent, in other words, what they *mean*.

    So from my perspective, it is nice to see this course operating on prong 1, but I’d also like to see more work on prong 2.

    • For several years, I taught a course that doesn’t quite fit the “build-your-own-relevant-statistics-course” as described in Andrew’s post, but I think it’s in the same ballpark, and I think it is in the spirit of gec’s two prongs.

      It was a probability and statistics course for students in a master’s program for secondary math teachers. The students had already taken a very minimalist online “stats 101” type course, so I could assume a little familiarity with concepts, and hence spend more time on other things. Students also had a calculus background, so I could use that as needed (and also to illustrate use of math topics, such as indefinite integrals, in areas of application to real world problems). I really wanted to focus on interesting applications, and since virtually everyone has had experience with medical diagnoses and procedures, I figured I would focus mainly on that, but also include other “might be in the news” topics like unemployment, poverty, etc.

      It worked out very well in several respects. The students were really engaged, and asked good questions.

      I made good use of external web links to things like different measures of “poverty”, “unemployment”, and “bone density” to point out the importance of being explicit in defining your terms and choosing your measures.

      Online simulations and other sites also helped students understand concepts like confidence intervals, the central limit theorem, and lognormal distributions.

      A Scientific American article gave ideas and examples for an approach to logarithms that several students said made more sense to them than the rote approach they had learned — and some said that they intended to use that new approach in their own teaching.

      Gegerenzer et al’s paper Helping Doctors and Patients Make Sense of Health Statistics gave ideas for engaging probability problems that provided a nice pathway to introducing some basic Bayesian statistics — and the students seemed to the students seemed to take well to the Bayesian ideas.

      In case anyone is interested in further details: I’ve still got some handouts from the class at https://web.ma.utexas.edu/users/mks/ProbStatGradTeach/ProbStatGradTeachHome.html

      • Awesome, thanks for sharing! I particularly like your diverse range of examples and wish this was something more stats texts did (instead of always being about surveys or test results). Pretty much any student is going to find something that speaks to them and gives them an entry point into the larger edifice.

  2. From her CV:

    Manuscripts in Preparation
    “Build-Your-Own-Statistics-Course” (with Andrew Gelman)

    So I guess this is further along than when you wrote the post. Any further details?

    As to her project, personally I would find it hard to study the holocaust. Lost too many relatives. Old enough to remember seeing relatives and family friends with number “tattoos” on their wrists. At least back then, few wanted to talk about it, and I can imagine why.

  3. I have another interesting idea.

    A small sample size of students happen to be global learners. These types of learners seek or ‘encode’ information in connections, or need to see the big picture first. Once they see the connections, and how one idea relates to the other, they can make sense of the details and individual concepts.

    Unfortunately, the education system doesn’t cater to these individuals.

    I would say that the best way to inculcate these students in the education system is to teach with this method: Begin with a brief survey of the entire course and emphasise how ideas relate, or connect, to each other. After that, students may be entertained with the specific type of problems related to these connections. Then, the usual step-wise method may be followed.

    This method can be applied in the Statistics courses at Columbia in order to be inclusive of all types of learners.

  4. From the course description, this does seem like an over-promise “identify appropriate methods for different research puzzles”.

    Give most researchers (and many statisticians) regularly fail here – should this even be suggested in a first course?

Leave a Reply to Martha (Smith) Cancel reply

Your email address will not be published. Required fields are marked *