Font Size: 

The Lee-Carter method and its later variants are widely accepted probabilistic approach for forecasting mortality and life expectancy in industrial countries due to their simplicity and availability of long time series data with better quality. This model assumes an invariant age component and a linear time component for forecasting, where the time component is adjusted for total number of deaths. We propose to apply the Lee-Carter method on smoothed mortality rates obtained by LASSO type regularization and hence to partially adjust the time component to match the observed lifespan disparity. Smoothing by lasso produces less error during fitting period compared to other spline based smoothing techniques. As a more informative indicator of longevity, partially matching with lifespan disparity made the time component more reflective of the mortality improvement. The suggested modification generates less forecast errors for mortality rates for many lower mortality countries and more accurate life expectancy forecasting for several high-mortality regime.

Mortality forecasting; Mortality smoothing; Lifespan disparity; LASSO