All Cause Mortality in England & Wales (15 – 44y)+
Smoothed Series Exploration
A subscriber has splendidly asked if I have looked at smoothed data for this noisy series. My answer was that I have been peeking at several smoothed variants. With a fresh pot of tea to hand I decided to try and settle on an ‘ideal’ smoothed series this very morning. Herewith the result…
This series was generated using the T4253H smoothing process. For those not familiar the smoother starts with a running median of 4, which is centred by a running median of 2. It then re-smoothes these values by applying a running median of 5, a running median of 3, and Hanning running weighted averages (span 3). Residuals are computed by subtracting the smoothed series from the original series. This whole process is then repeated on the computed residuals. Finally, the smoothed residuals are computed by subtracting the smoothed values obtained the first time through the process. A bit of a mouthful I admit, but there is a useful summary here and here with nowt to be found on Wiki!
We can now see why the series is not a random walk, and we can see that long-term periodicity is becoming apparent. The kick upward in recent weeks is looking worrying but the old trick of rule-of-thumb suggests it is still too early to detect a genuine change in the underlying rate; then there’s the elevated rates for 2010 to consider, and goodness knows what else prior to 2010!
When I can find time I shall brush the dust off weekly data going back to 1970 to see what we can see, but the headache is that I’m unlikely to obtain reliable population estimates for the 15 - 44y group this far back.