DiD Spending Model: Retirement Due to Corruption

[JohnCRuf]

So, the close elections DiD estimator found robust null results.
This could be because close elections necessarily drive Aldermen towards median voter-style outcomes.
In a typical city, we'd be SOL with no way to boot out entrenched incumbents exogenously.
Luckily, this is all happening in Chicago so that we can use investigation-forced retirements as potential treatments.

The idea is to take the population of "entrenched" incumbents (ie, those who are unchallenged or win by extremely large margins) and compare them to the sample of aldermen forced into retirement by corruption allegations/investigations.

[JohnCRuf]

From this list: https://blockclubchicago.org/2021/04/30/a-list-of-chicago-aldermen-indicted-raided-or-implicated-by-the-feds-criminally-charged-or-convicted-since-2019/

Burke, ward 14, 2023 (out of sample unfortunately)
Patrick Daley Thompson, ward 11, 2022
Ricardo Munoz, ward 22, 2019
Danny Solis, ward 25, 2019
Proco Joe Moreno, ward 1, 2019
Willie Cochran, ward 20, 2019
Michael Zalewski, ward 23, 2018

Jesus fucking christ.

[JohnCRuf]

https://www.cbsnews.com/chicago/news/alderman-burke-chicago-city-hall-corruption/

Sandi Jackson, ward 7, 2013
(Coincidentally, William Beavers was also convicted that year, also from the seventh ward but left)
Ike Carothers, ward 29, 2010
Arenda Troutman, ward 20, 2008
Carrie Austin, ward 34, 2022

[JohnCRuf]

How are there more aldermen booted out of office from corruption convictions than from runoff elections?!

[JohnCRuf]

So if I use all the cases outlined here, we're at a treatment group size (total) of 8. 11 when the 2023 data comes in. This is already almost 3 times larger than any of the close election DiDs.

So the treatment group will be ~ 8 * 5 * 17 = 680 observations

New looking at all the aldermen elected before 2000:

Anthony Beale, ward 9, 1999
Emma Mitts, ward 37, 2000
Walter Burnett, ward 27, 1995

And we can probably add in Ed Burke, Carrie Austin, and PDT

This add 6 * 5 * 17 = 510, leading to a total observation count of 1190. Triple of any of the close election estimators.

The only question is how to make it work through redistricting. May just be worth it to slice out the pre-2012 alders to maintain consistency.

[JohnCRuf]

So I currently have some kinda-decent results but they don't fully exploit the full potential of the number of corrupt aldermen.

I need to ``retrofit'' the 2012-2015 map to the 2005-2011 data. That's the only way to get the standard errors down to something reasonable.

[JohnCRuf]

Closed with #42