We talked about this a couple of months ago, but now the time is nigh to build and create an on-line statistics course, or courses.
There are several problems: content, manner of delivery, costs, credit or acknowledgement, advertising. I’ll sketch my thoughts and request yours.
Content
Statistics ranges from pure philosophy to pure mechanics, and I have the idea that more people would enjoy the latter. I mean, I could offer courses on epistemology, philosophy of science, point (God help us) estimation, measure theory, Bayesian theory, and the like, with more or less technical content, but I think the audience for such material is limited, and those wanting it are more anxious for “credit”, discussed below.
Instead, my guess is that practicum would be more popular. Courses like: Introductory Data Analysis, Introduction to R, Advanced Modeling, Regression, Predictive Analytics, and the like, again with more or less meatiness depending on the audience.
Therefore, at the start, I propose three: (1) Introduction to the New Statistics: Bayes, Prediction, and All That. (2) Introduction to R. (3) Philosophy of probability. If you have other suggestions, please do list them below. I’m open to most things.
Introduction to the New Statistics: Bayes, Prediction, and All That
A sketch of the two major philosophies of probability, settling on the correct one (probability as logic, Bayesian statistics). Evidence, argument, logic. Learning to count. Basic probability models. Uncertainty. Modeling: regression and logistic regression. Students must find, present, and explain their own data sets, with guidance and within certain limitations. A project where this data is analyzed and explained fully, complete with an explanation of the many reasons why they results might be wrong, comprises the grade. This is the course I teach, to some success, at Cornell, even though I say it myself. The R software (free) will be used, but the computer work is not the main focus.
Introduction to R
Reading in, storing, outputting, and manipulating data. GUIs, why they’re nice and why they should not be used. Data frames, variables, basic coding, modeling, graphics (base, lattice, introduction to ggplot2). The world of packages (plug-ins of analysis software, all freely available). Interacting with JAGS, Excel. A project comprises the grade (a file or files of code designed to do a set task).
Philosophy of probability
A reading and discussion course, with some but minimal lectures (videos). Sketch of authors list (incomplete): Aristotle, Laplace, Keynes, Hacking, Ramsey, Carnap, Jeffreys, de Finetti, Howson & Urbach, Williamson, Stove, Jaynes. Plus a few more modern papers. Some of these are too technical or mathematical, so only select pieces of authors are used. A paper—and a phone call with me—discussing some aspect of probability comprises the grade.
Manner of delivery
I could do the whole thing here, on a separate room on the site, complete with videos, emails, chat sessions and so forth. Or I could use a site like Udemy or StraighterLine. The advantage to sites like these are: infrastructure already in place, easy to create courses, possibility of “credit”, billing outsourced, and so forth. Disadvantages are courses can get lost (there are many on offer), have to share the money with the site, they are a little more impersonal.
Another advantage is the material is all paced at your ability. The course does not have to start and stop in (say) twelve weeks for everybody. Some might blaze through in six, others might take fifty-two; others might join in the beginning and then leave, or more might skip the intro and wade in downstream. All would be fine.
Costs
It’s got to cost something. How much? That is, what weight of green stuff are you willing to part with to take these courses? Let me know below. When answering, remember the beauty of the phrase, “Give ’till it hurts.” Good news is that different courses can cost different amounts. The Philosophy of Probability course would be cheapest, because most of the burden of the material is on you, the student. The others would cost more because they’d take more of my time.
Credit or acknowledgement
At the least, anybody who takes a course with me could always ask for a letter or a phone call as acknowledgement they took the course, and where I could give my opinion on the student’s ability. I could always devise a certificate; the sites like Udemy have such a mechanism already in place. They also have approaches to (and here is where it gets complicated) official accreditation, wherein courses might—I say might—transfer in part or in whole to more formal institutions of higher learning. Instead of me going on about this, I encourage you to wade through the sites linked above, or this article, and learning more.
Advertising
How best to get the word out? It would be quite an investment of my time to create the course, particularly the first two, so that they fit well on-line. I’d hate to make this investment if I can only find a handful of students. Advertising is where I’m at my weakest. I’m terrible at blowing my own horn, finding it embarrassing. Yet this is how one must get on, so I’m prepared to do it. I just don’t know how.
All ideas welcome. I envision, if all goes well, beginning this or these courses early next year, perhaps February or March. Thanks everybody!
Hi,
I agree with your introductory courses. I would take them all. I interested in a certificate issued by you as I don’t need an external or so called recognized diploma. Probably the outsourced solution is better for you but I would take the class regardless. I have no idea about the price but I am willing to spend my allowance of about $100 monthly as long as it takes. A note about my needs: I am in information security so data manipulation, risk, and other metrics are essential. Also R could be useful for my economics hobby. Regards, Daniel
I would be interested. The philosophy of statistics would be my first choice. I have no idea for what the cost should be, but I would find a way to cover it. This would be just for my own personal learning, so a certificate would be fine.
I’d definitely be interested if it were rigorous and self-paced (within reasonable limits).
Causality. At lest an introduction. Your students need to understand that fitting a curve does not prove the theory. That’s wandering into philosophy though.
GUIs, why they’re nice and why they should not be used.
I suppose you mean the ones providing pushbutton analysis.But Rterm is plain awful. It’s like looking through a peephole and makes you trample on your output to get things done. Something like StatET combined with Eclipse is a GUI that makes sense.
Looks like you will be competing with this. That’s strong competetion.
http://www.khanacademy.org/
(1) and (3) would be really nice. R is widely discussed in the net, with lots of tutorials, perhaps is not that needed. About the cost, if you make it too personal (ie, not automatic), you will not be able to have a massive course, and the price might be too high for most people. I would pay $100 for a well organized ‘coursera/udacity’-like course for (1).
Ray,
Khan is interesting, but not always correct. His econ classes sometimes fall short.
There are already several good and free intro to stats and R courses available online (check out coursera and udacity), so I am skeptical of charging for those. In my opinion, your best target audience is practioners who learned frequentist methods in school, but want or need to learn Bayesian methods. I don’t beleive I’ve seen any comprehensive Bayesian courses for free.
So, with that in mind, I might rename your stats class something like, “Relearning Statistics from the Bayesian Perspective.”
And make a follow up course, Bayesian Modeling and Computation, that covers MH, Gibbs, etc using R and Bugs, or whatever you use.
You could even make an Advanced Bayesian Modeling class that covers Multilevel Models and whatever other advanced models you use.
To summarize:
– the market for introductory R and stats classes are already saturated with free options.
– to find people who are willing to pay, market to people who make money using statistics, but whose education is stale and dated
– to command a fee, depth will be better than breadth
What is your objective? Who are your customers? Is this to be an Omega or a Timex? You better answer these first before you put finger to keyboard.
I suggest you survey some of your former students about how they use what you taught in their current professions. Then target that audience of professionals who could benefit from the knowledge in their work. Attractive features of what you offer are the flexibility, pacing, and personal interaction. These are needed by people who are juggling work and family commitments and feel constrained by the semester structure and impersonal tendencies of online course. Content is the core, but you also are selling service.
Readers may be interested in this piece from Walter Russell Mead at Via Media …
William Briggs is therefore in the “smart professor” group.
I don’t know a lot about statistics but I enjoy reading some of the articles on here and some other sites – the recent article about the three doors is an example – if you have a topic maybe reference some interesting article about the topic as a way of learning how to think about the topic …another didactic course is not needed …something more about how to think our way thru stats questions maybe
Udacity founder Sebastian Thrun does a Statistics 101 course. I haven’t taken it, but it looks like it starts with Bayes. http://www.udacity.com/overview/Course/st101/CourseRev/1
Mr. Speed
There is incessant talk about the edu business. But it is just that. The world has been successfully moronised in the past thirty years. No change is expected. As for weather Mr. Briggs is really smart or not I can’t judge. But I know that he prefers quantity over quality
George Steiner,
He also prefers “whether” over “weather” when desiring a conjunction.
All,
Thanks for the tips and suggestions. Keep ’em coming!
Just some random thoughts:
Your writing (and presumably your speaking style, as well) are very good, so bode well for quality of presentation in your courses. No doubt you “know your stuff”, so your judgment on course structure is probably spot-on.
As a consumer of texts on matters such as math and statistics, I can’t help but notice that there is a spectrum of styles: theorem/proof recitations that make you think really hard about the motivation for any theorem, because it’s only hinted-at, at best; and texts that offer watered-down theorems with no proofs for those who just want to know how to “do” statistics (or calculus, or whatever). When choosing a point along that spectrum, it’s probably useful to have a very firm grasp of the purpose of the course: who would take it, and why?
I’m guessing that there would be a greater potential audience of people who would take the course for practical reasons rather than for the intellectual satisfaction of understanding *why* a particular technique works and thus what its limitations are. While it might be more extra work than it’s ultimately worth, easily-accessed, supplemental “behind the curtain” materials that provide the rigor, should you choose a “how-to” format, would be a great feature for some.
While it also may be more extra work than it’s worth, well-integrated, interactive, graphical materials (e.g. show how the curve changes as you vary the parameters of the distribution)could add the “sizzle” that serves as the differentiator between your course and others.
With video materials, I would tend to steer away from a talking-head at a whiteboard, or textual bullet-points. Animations that directly support the audio are probably a more effective learning tool. Of course, they’re expensive, too, so that may dampen your enthusiasm for them.
Of course, if you choose the how-to route, providing some way for your audience to practice on their own is probably an essential. So, the question is what platform would you recommend? Some are powerful but rather more difficult (R), some are relatively easy, but maybe a bit rigid (Microsoft excel). Other are expensive. The problem then becomes how to avoid devoting too much capital to the mechanics of the tool, vs. the material at hand. Developing a purpose-built back-end that is sufficient to illustrate the concepts but also simple to use could be an option: build in a few datasets and whip up some JS code to do some common computations.
Anyway, best of luck — it’s an ambitious undertaking, but one that I am sure you can tackle with good effect!
How about how to approach experimental design?
Reading the comments, I wonder how many different levels of learning each of us represents. When you are speaking of “introductory”, what level would that be? First year college?
Just becareful what you offer to the residents of Minnesota.
Coursera has been informed by the Minnesota Office of Higher Education that under Minnesota Statutes (136A.61 to 136A.71), a university cannot offer online courses to Minnesota residents unless the university has received authorization from the State of Minnesota to do so. If you are a resident of Minnesota, you agree that either (1) you will not take courses on Coursera, or (2) for each class that you take, the majority of work you do for the class will be done from outside the State of Minnesota.
George Steiner …
Whether the weather be fine
Or whether the weather be not
Whether the weather be cold
Or whether the weather be hot
We’ll weather the weather
Whatever the weather
Whether we like it or not.
It’s interesting that the high power, wealthy and well regarded schools such as Harvard and MIT, which have incredibly talented students in line hoping to gain admission, are taking high-efficiency (low(er) cost per student) instruction seriously while the hundreds or thousands of small schools scattered around the country, those having the most to lose by not acting as well as the most to gain by bandwagon jumping, aren’t. Wal-Mart didn’t become the world’s largest retailer in a day nor did America’s mom and pop retailers lose all their customers overnight but the effect was the same as if they had.
Briggs …
Please design a feedback system into your venture so that you will learn what works and what doesn’t; where students are having problems and where they are succeeding; and what should be cut and what added.
Speed,
What is the largest university in America?
The University of Phoenix, by a huge margin.
Expanding on Doug M’s comment, the University of Phoenix enrollment is 307,871 (fall 2011) and number two is Ashford University (also for-profit in the traditional sense) at 74,596. These are DOE numbers via Wikipedia.
Interestingly, CUNY claims to have 540,000 spread over 24 “institutions.”
http://en.wikipedia.org/wiki/List_of_largest_United_States_universities_by_enrollment