Information Matrix

Filter

Posts feed
Publication date

Stabilising projections

With many stochastic models of mortality, projections of future mortality rates are done using a time series.  In a landmark paper, Currie, Durban and Eilers (2004) introduced the idea of using P-splines as an alternative means of generating a forecast.  P-splines formed the basis of a projection tool the CMI made fr

Written by: Stephen RichardsTags: P-splines, time series, mortality projections, CMI

The Lee-Carter Family

In a recent paper presented to the Faculty of Actuaries, Stephen Richards and I discussed model risk and showed how it can have a material impact on mortality forecasts.  Different models have different features, some more desirable than others.  This post illustrates a particular problem with the original Lee-Carter model, and shows how it can be combatted via smoothing.  The choice of which parameters to smooth in the Lee-Carter model leads to a general family

Written by: Iain CurrieTags: model risk, Lee-Carter, mortality projections

Expectations v. extrapolations

The CMI has published two working papers along with its new mortality projection model.  The proposed new model blends current improvement rates into an expected long-term average rate of improvement.  The hope is that such models can incorporate expert opinions on mortality trends to improve the accuracy of projections.
Written by: Stephen RichardsTags: CMI, mortality projections

Basis risk in mortality projections

In a recent paper Stephen Richards and I discuss the effect of model choice on mortality forecasts. Our approach is quite low key: we look at just three models, all members of the Lee-Carter family. Nevertheless, our findings are quite dramatic: even within this very small family the differences in the forecasts really matter financially. So model choice matters.

Written by: Iain CurrieTags: basis risk, mortality projections

Influenza and coronary heart disease

 Every good statistician knows that correlation does not imply causation.  Just because two things appear linked does not mean they are. However, with historical data we often don't have the luxury of carrying out controlled, scientific experiments to see if A really does cause B.
Written by: Stephen RichardsTags: influenza, CHD, mortality projections, Spanish influenza pandemic, ICA, stress test, cause of death