Working Paper 20 - Stochastic projection methodologies: Further progress and P-Spline model features, example results and implications

This Working Paper provides an update on the work of the CMI's Mortality Projections Working Party. The paper includes the feedback received to Working Paper 15 and the Working Party's responses to this feedback plus a summary of the CMI's activity in this area since WP15 was published.

Subsequent sections of this paper provide more detail on the P-Spline methodology, including:

• A description of the models and datasets used;
• A guide to using the output from the P-Spline modelling software made available by the CMI;
• A discussion of various features of the P-Spline models and guidance on parameterisation of the P-Spline model;
• Sample annuity values for use in 2004 produced using the P-Spline projections and data to 2003 which are then compared to annuity values based on the interim cohort projections, plus how the equivalent sample annuity values for use in each year between 1993 and 2004 would have progressed as more data became available over the period;
• Tentative conclusions regarding the P-Spline methodology; and
• Next steps.

The CMI has sought to make the research more accessible to actuaries through Working Paper 30 and the CMI Library of Mortality Projections. For more details, please click here.

The CMI has made available the illustrative software it used in its research into mortality projections. The software is not commercial grade but is intended to allow users to experiment with the methodologies. For more details of the software please click here.

Subsequent to the publication of Working Paper 20, the CMI became aware that the dataset for Permanent Assurances for Male lives used included initial exposures but was used as if these were central exposures. As a result, the results published in Working Paper 20 (and Working Papers 25 and 27) that used this dataset were inaccurate.

To obtain more details on this issue and its impact, please click here.

Working Paper 20 has been revised to take account of this issue. To access the revised version of Working Paper 20, please click here. Please note that this version of Working Paper 20 has NOT been updated for any developments subsequent to its original publication, other than the noted errata. Should you require a copy of the original version, please contact the CMI.

Back to the CMI Home page