Information Matrix

Filter

Posts feed
Publication date

Parallel (Va)R

One of our services, the Projections Toolkit, is a collaboration with Heriot-Watt University.  Implementing stochastic projections can be a tricky business, so it is good to have the right people on the job.
Written by: Gavin RitchieTags: parallel processing, technology

Groups v. individuals

We have previously shown how survival models based around the force of mortality, μx, have the ability to use more of your data.  We have also seen that attempting to use fractional years of exposure in a qx model can lead to potential mistakes. However, the Poisson distribution also uses μx, so why don't we use a Poisson model for the grouped count of deaths in each cell?
Written by: Stephen RichardsTags: survival models, Poisson distribution, GLM

Following the thread

Gavin recently explored the topic of threads and parallel processing.  But what does this mean from a business perspective?
Written by: Stephen RichardsTags: parallel processing, simulation, Solvency II, technology

Competitive eating

I've previously suggested parallel processing might have a touch of the infernal about it, and further evidence might be how it allows us to usefully indulge in one of the seven deadly sins, that of gluttony.
Written by: Gavin RitchieTags: parallel processing, technology

Longevity and the 2011 Census

The Continuous Mortality Investigation (CMI) has just announced its decision to postpone the release of its mortality projection model until 2013, the main reason being to properly allow for the impact of the 2011 Census.

Written by: Richard WilletsTags: mortality improvements, census

Extracting the (data) value

Risk management is about properly understanding your risk factors and managing accordingly.  In a modern actuarial context, this is about a lot more than a simple comparison against a standard table.
Written by: Gavin Ritchie

Canonical correlation

At our seminar earlier this year I looked at the validity of assumptions underpinning some stochastic projection models for mortality. I looked at the assumption of parameter independence in forecasting, and examined whether this assumption was borne out by the data. It transpires that the assumption of independence is a workable assumption for some models, but not for others. This has important consequences in a Solvency II context — an internal model must be shown to have assumptions grounded in fact.

Written by: Iain CurrieTags: VaR, smoothing, mortality projections

An early bath for the bathtub model

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.
Written by: Stephen RichardsTags: survival models, mortality, bathtub hazard

Actuarial exceptionalism

In an earlier posting I listed some actuarial terms and their statistical equivalents (and later a short list of statistical terms and their equivalents in other fields).  Using different expressions for the same concept is an unfortunate barrier to understanding across disciplines.

Written by: Stephen RichardsTags: survival models, left-truncation

Trend risk and age

There are several ways of looking at longevity trend risk, as covered in our recent seminar. However, regardless of how you choose to look at this risk, there are some pitfalls to watch out for.
Written by: Stephen RichardsTags: Solvency II, ICA, longevity trend risk, model risk