Stan and BDA on actuarial syllabus!

Avi Adler writes:

I am pleased to let you know that the Casualty Actuarial Society has announced two new exams and released their initial syllabi yesterday. Specifically, 50%–70% of the Modern Actuarial Statistics II exam covers Bayesian Analysis and Markov Chain Monte Carlo. The official text we will be using is BDA3 and while we are not mandating the use of a software package, we are strongly recommending Stan:

The first MASII exam will be given in 2018 and things may change, but now that the information is been released I hope you find this of use as a response to your requests for “Stan usage in the wild.”

The insurance industry isn’t the wildest thing out there. Still, I’m happy to hear this news.

4 thoughts on “Stan and BDA on actuarial syllabus!

  1. If my experience with actuaries is representative, hundreds of actuarial students will now cram enough of BDA into their brains to pass the test and then, like the material on the other tests, promptly forget it about it for the rest of their career. Maybe it’ll sink into a few of them, though.

  2. Hey, I resemble that remark!

    Speaking as someone who survived the exam process, I partially agree with you. Then again, remember that the exams are not only meant to test that one has achieved a the “minimally qualified actuary” level of competency, but also to expose the actuary to the tools which he or she may use in the future. Even if a large segment of actuarial candidates will forget the details two weeks after the exam (which is not dissimilar to under/grad students, no?), they will have seen it, and in a correct and reasonably rigorous setting, and one day, they will be faced with a problem which will jog their memory and they’ll blow the dust off of BDA3 and start putting it into practice.

    I can speak from experience that having been exposed to the concept of MCMC Bayesian analysis years ago, even though I didn’t have that deep of an understanding, allowed me to address a problem an insurance company was having in finding the necessary support to justify changing their long-term risk estimates (and thus needed budget) for a particular segment of business. I eventually turned that, completely sanitized, into a peer reviewed paper, and that is how I stumbled into Stan in 2014 :).

Leave a Reply to Chris J Cancel reply

Your email address will not be published.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