Post-Election Campaign Narrative
Disclaimer: For this cycle, I did work on Angie Craig’s campaign, so I may have a slightly biased view of what occurred. The statements that I make should not be taken as statements from the campaign. This largely comes from my own opinions and research of the events and news coverage, as well as knowledge from the class Gov 1347. Introduction Throughout the 2022 midterm elections, I closely followed the race in Minnesota’s 2nd Congressional District between Angie Craig (D) and Tyler Kistner (R).
Reflections on Final Election Predictions
Introduction Now that the election is over, it is possible to evaluate how my model has done when it comes to the election. First, I’ll take a look at overall measures of accuracy, then look at district-level accuracy, then explore trends in the misses and the correct calls that I made for the election. Model Evaluation To begin with, there is an important error that I only caught after the election itself.
Final 2022 Midterm Election Prediction
Introduction My final prediction for the election is a product of research and investigation through the series of blog posts that I have done prior to this week, investigating how factors like polling, the economy, and incumbency affect election results. As my final model, I use an ensemble model that combines two main things - first, a pooled model that contains the last decade of elections, and second, a partisan lean for the district that is calculated through recombining election results in the new district post-redistricting.
Further Model Improvements (Week 7)
Introduction Since we are now approaching the election, the primary focus for this week will be continuing to improve the model that I’ve been building week to week. My focus this week will be in exploring three major things. First, I look to improve the district-level model from Week 6 by adding an interaction term between the economy and incumbency as well as some other fundamental indicators for the districts.
Adding Turnout to District-Level Predictions (Week 6)
Introduction This week we examine the ground game by campaigns. Campaigns are primarily occupied with persuading voters to vote for them and turning out people that already support them to vote. We looked at persuasion last week through television ads, but for this week, we’ll be examining the turnout factor instead. Academic literature has found that having field offices in a county increase that county’s vote-share by about 1% in the 2008 election (Darr & Levendusky, 2014).
Media and Campaigns (Week 5)
Introduction So far, the blog posts have covered things that are largely outside the direct control of campaigns - to the tune of the economy, polling, and expert predictions. We now move to something that campaigns can directly control - the air war, or that advertisements that campaigns will put out on television. We know from previous research that television ads can and do affect voters, particularly through priming voter preferences, though these effects may only be on the short-term (Gerber, 2011).
District Level Expert Predictions (Week 4)
Introduction This week, we look at the inclusion of expert ratings, as well as incumbency. There are numerous political experts that will provide ratings for the political lean of a district per election. These political ratings can be put into a model for predicting the election that will improve the accuracy of the model and take into account things that we may not be able to account for in the model, like general sentiment or on-the-ground insider knowledge.
Election Polling (Week 3)
Introduction Polling has been an essential party of the run-up until elections for a number of decades now, and are a way of gauging national sentiment throughout the election. While polls do have error and have failed to correctly determine the winner, with the 2016 presidential election being the most salient example of this in recent memory, they continue to be a good barometer on national sentiment and have improved through methodological changes.
Effect of the Economy on the Election (Week 2)
Introduction The aim for this week’s blog post is to understand the force, if any, that economic variables have on the election. Our understanding of the presidential election is largely shaped around the election. Researchers Christopher Achens and Larry Bartels have found that economic growth, particularly in the last quarter before the election, is highly correlated with the success of the incumbent president (Achen and Bartels, 2017). This model of voting assumes that the voter is rewarding or punishing the president for their ability to manage the economy, but that they’re slightly myopic and don’t take into account the whole term.
Introduction to Election Analytics (Week 1)
Introduction This series of blogs leading up to the 2022 US Midterm Elections will aim to predict the outcome for the House of Representatives. This project was created in Gov 1347: Election Analytics, a course taught by Professor Ryan Enos at Harvard University. This first blog aims to explore the two-party vote-share margin and vote swing for the House of Representatives in order to identify changes in voting between the 2014 and 2018 midterm elections.