[theophrastus]

I wonder what sort of bias might be introduced by starting out with those who bought life insurance? At the least this likely under represents folks at both ends of the wealth spectrum.

[folli]

So you're proposing a correlation between wealth and the date of birth?

[theophrastus]

more along the lines of wondering if to be included in the analysis requires buying life insurance if that results in a properly random sample of the entire population