Thoughts On An Old FASS Paper
Stephen and our late and much-missed colleague Iain Currie each once marked the presentation of a paper to a sessional meeting of the IFoA by penning some verse for the dinner that followed. The recent presentation of Macdonald & Richards (2024) therefore provided my excuse for the following lines.
Student actuaries of old
Were horrified when they were told
That standing firmly in the way
Of getting letters F.I.A.
Was an exam of some repute
The sentinel of the Institute
They studied hard and studied late
But to a woman grew to hate
Those probabilities of dying
It wasn’t down to lack of trying
Students smart and students able
Were tripped up by that old life table
They learned the likelihood equation
And tests for any graduation
They plotted points, they plotted lines
They fitted curves, they fitted splines
’til Cox’s model held no terrors
Nor Cairns-Blake-Dowd, nor standard errors
Then came the day, at last their maths
Did satisfy those psychopaths
Examiners! who’d seemed so tough
Cried “go away, we’ve had enough!”
At last they said, with happy sigh
We’ll leave it all to the C.M.I.
So off they went on their careers
To spend their most productive years
Buying, selling, funds investing
Pricing, valuing, profit-testing
Doing the actuarial things
that lots and lots of money brings!
Maybe even, if they should dare
A seat on Council \(\ldots\) and why stop there?
But wait! A rumour from the North
Two actuaries, beside the Forth
Are being quite foul to poor old \(q\)
And saying “you should be using \(\mu\)”
Products once were things to sell
But now they’re integrals as well!
They should replace those old additions
Get rid of years of fond traditions
Raise a stink, and start a hooley
It’s Pascal out, and in, BERNOULLI
(The irony will not be lost
The maths is that of coins tossed
There is no need to end this fable
With rolling dice, and six-fold table)
So here we are, a sessional meeting
Some learned talk, then down to eating
But far from squashing those two sinners
You have just paid for both their dinners
References:
Macdonald, A. S. and Richards, S. J. (2024) On contemporary mortality models for actuarial use II - principles, British Actuarial Journal (to appear).
The old FASS (Faculty of Actuaries Students' Society) paper referred to contained The Story of the Tossers mentioned in this earlier blog.
Previous posts
Actuaries got there first
Regular readers of this blog (both of them) will have noticed how often we advocate that actuaries use the Kaplan-Meier estimator in their mortality analysis. While parametric survival models are best for multi-factor models, the Kaplan-Meier estimate is exceptionally useful for visualisation, communication and data-quality checking.
Inexplicable, Say I
Stephen recently questioned whether the hype around AI models for Life Insurance might be a case of The Emperor's New Clothes. In this blog we discuss an important point of difference: whereas in the fable, a youth reveals the expensive "invisible" new clothes have no substance at all, in our scenario, we find precisely the opposite. AI models utilising machine learning are, far from being see-through, simply not transparent enough.
Add new comment