[timr]

That doesn't "take it into account"...it just plots them, based on which presidential candidate the county voted for. And by looking at the plot, it's clear that age-adjusted mortality rates are almost perfectly aligned for rural democratic and republican areas until 2009, when they drop suddenly for the democratic areas. Then they both continue tracking in parallel. Why is that? Can't tell. Sure is suspicious. Could it be that a bunch of counties flipped in 2008?

I skimmed this paper to see if the authors did any of the facepalm-obvious things you'd do to control for covariates if you were serious about doing an observational analysis (e.g. multi-factor regression), but saw nothing. They're literally just looking at differences in slopes in the lines:

> Trends in mortality were examined to identify changes in slope using Joinpoint Regression Program version 4.8.0.1, which models consecutive linear segments on a log scale, connected by joinpoints, and can measure when slopes of annual percentage change (APC) undergo a statistically significant change

This is a...well, let's just call it non-conventional...analysis method.