Information Matrix

Behavioural risk factors such as smoking and excessive alcohol consumption are significant drivers of mortality and morbidity.

Earlier this week I had the opportunity to attend a New Scientist: Live presentation given by Sir Harry Burns entitled "Making Scotland Well Again", which was an examination of the links between social conditions and incidence of disease.

We've talked repeatedly about a key advantage of statistical models over deterministic ones — specifically, that they provide confidence intervals in addition to a best estimate.

Given my birthplace, I have a more than casual interest in the causes of excess mortality experienced by Scots beyond that explicable by deprivation alone.

Experts can come in for a lot of criticism, but they have their uses. After all, with no heads above those parapets, humanity would neither see so far nor have enough target practice.

My last posting looked at why actuaries fitted survival models differently to statisticians, even though the conceptual framework for survival models is common to both disciplines.

The CMI recently asked for an overview note on survival models.  Since this subject is of wider actuarial interest, we wanted to make this publically available.

Mortality statistics occasionally make the news, usually with some eye-catching statements.  Here is a recent example from the BBC: "Data from life insurance companies suggests that in the fifth and sixth decades of life you are less likely to die over the coming year than at any other time in your life."

We've created a short graphical summary of the application of postcode-driven lifestyle within actuarial mortality models.