poly: Why we die?

The study about the causes of death contains enough things
that contradict "well-known" health information that I am
wary of accepting it as accurate: At the minimum, the authors
and I must differ on vocabulary.

[If taken at face value, it implies that any other study
about causes-of-death must *exactly* match control & target
populations for wealth, to avoid swamping the more subtle
effect being studied.]

The various factors studied are mostly strongly correlated,
(wealth & age being an obvious example), and even defining
single variable effects is tricky.

I imagine that asking people at random "How are you?" would
be a fairly good predictor for longevity, but I don't pretend
that the replies affect health.

I look forward to careful dissection of the study claims --
after proper normalizations, there may be a kernel of truth.

Rich Schroeppel rcs@cs.arizona.edu
Received on Mon Jun 29 19:59:50 1998