I also understand linear regression, and it is still not the issue with taking the mean/median of the last 5 years and using it as your comparator point for 2020 excess mortality
-
-
I'd suggert that
@TedPetrou validates his method by using it to calculate the expected deaths *of the previous years* (like 2016, 2017, 2018, 2019) using his method of considering rates from a suitable but fixed number of years prior, similar to what he did for 2020. -
If you think it is a good idea, please suggest it to
@TedPetrou as I have been blocked by him, and he will not see my posts. Thanks.
End of conversation
New conversation -
-
-
The issue is that you weren't thinking about intervals. Theres no guarantee that Sweden mortality would decline because of historical trend. The rate of decrease has slowed. 2018 mortality rates give you just about 96k deaths. You cannot dismiss this as a possibility.
-
In the same vein, you cannot discount the possibility that 2019 was not an anomaly and that the mortality drop was part of a trend, which would mean a death rate of roughly 88k and excess mortality of 10k. Uncertainty cuts both ways
- Show replies
New conversation -
-
-
88k deaths would be an elderly decrease of ~12% over a 2 year period. This would be by far the largest 2 year decrease in the last 20 years. 2019 was already the largest decrease in the last 20 years for the elderly. Going back to back would be essentially impossible.
-
The last time that Sweden saw an increase in mortality of the sort you're proposing WITHOUT COVID between 2019-2020 was I believe 1944. They are both equally implausible, but if you're going to embrace the uncertainty it's ridiculous to pretend it only goes one way
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.