Thread by @chrishanretty

Did Australian legislators who were out of step w/ their constituents on the issue of same-sex marriage suffer electorally in the 2019 election? A new WP by me and @jillesheppard says "no, not to any substantively meaningful degree" drive.google.com/file/d/1X6m0Us… #teamprecisenulls

Timeline:
2017: Postal Survey: en.wikipedia.org/wiki/Australia…
2018: votes on same-sex marriage
2019: federal election

We tackle the question two ways. We look at individual level data, and find no sig. effect. -- but the individual level data is under-powered to detect an interaction effect of the kind we're interested in

We turn to aggregate data, and construct polling place catchment areas (black lines) using a ton of census districts (colours polygons)

We then interpolate area-level support for SSM, and use this to predict incumbent vote share in that polling place, given their stance on SSM

We find that if you're 13 percentage points (=1 SD) more "in-step" with your district, you gain a whopping 0.03 percentage points in vote share (95% CI: -0.31 to 0.38). Woot!

We then step back to the 2016 election, to see whether this was all priced in, and SSM-supportive politicians did better then in more supportive areas. Spoiler: they don't.

Possibly of interest to (people cited in the paper) @tabouchadi @PME_Politics @benlauderdale @jon_mellon @ShaunRatcliff @FSnagovsky