I wonder how Ozempic will change this? I really do expect we will all be on this soon and maybe we can resume the increase in lifespan that has been stalled by obesity, lack of exercise, and processed food.
replies(4):
Life expectancy is a weighted average (no pun intended), and so it's unusually sensitive to outliers. People who die early drag the average down much more than people who live close to the mean life expectancy. The biggest premature killers of Americans are obesity, drugs, car accidents, and suicide. Anything that addresses one of those causes of death has an outsize effect on life expectancy. There are 100M+ obese Americans. There are about 100,000 overdose deaths per year. Obesity, while not as lethal as drugs or suicide, afflicts 1000x as many patients, and so a treatment for it can have a large effect on the numbers.
Sure, if all the weights are 1. Where i come from, we just call that an average.
>People who die early drag the average down much more than people who live close to the mean life expectancy.
This is true of all averages where all weights are the same.
(To reproduce exactly the scenario being discussed, you fit a constant-only model to the data using least squares: that gives the average as the best fit. Then, you measure the leverage of each point of interest.)