Some ideas on communicating risks to the general public

Aleks points me to this research summary from Dan Goldstein. Good stuff. I’ve heard of a lot of this–I actually use some of it in my intro statistics course, when we show the students how they can express probability trees using frequencies–but it’s good to see it all in one place.

4 thoughts on “Some ideas on communicating risks to the general public

  1. You can check out the Teaching category on this blog. Also, I've published a book and about 15 articles on statistics teaching; the book can be ordered and the articles downloaded from my website.

  2. Andrew, a gem – thanks.

    I posted this comment there.

    Tried a few times to take the next step – allow people to experience Bayesian Inference by taking an observed result then drawing the unknown from a prior, then drawing fake data given that parameter and then just keeping those parameters drawn where the fake data equalled the observed result (hence a sample from the posterior).

    In a group, all of whom had graduate degrees (~ 1/3 Phds) they were very, very confused. Perhaps being given a batch of numbers (a sample from the posterior) as an answer to a quantitative question just seemed too strange to be sensible.

    But wondering if there is anyone doing research on grasping the posterior distribution (or a good sample from it) as an answer (inference) for those with little training in statistics?

    K?

  3. Emphasis on "the way Delong does intro macro", meaning, more intro-statistics tied in posts, more living, interactive, syllabus, lesson plan, reading list, and assignment type posts. It's a fan request, not a criticism.

Comments are closed.