Reflection on PA-07
Introduction of PA-07 This semester, I closely paid attention to the election happening in Pennsylvania’s 7th Congressional District, which featured a rematch between Democratic incumbent, Susan Wild, and Republican challenger, Lisa Scheller. In the end, Susan Wild won re-election with about 51% of the vote to Lisa Scheller’s 49%. There was a vote margin of less than 6,000 votes! Election Result History of PA-07 Due to the 2020 Census, Pennsylvania lost a seat in reapportionment and had to redraw their maps, which went into effect on February 23, 2022.
Post 2022 Election Reflection
Introduction This week, I reflect on my predictive model for the 2022 House of Representatives elections based on the actual results of the 2022 elections. To summarize, I predicted that the Democrats would win 216 seats, while the Republicans would win 219 seats, resulting in a slim Republican majority in the House of Representatives. After reflecting on and analyzing my model based on the actual results, I find that my nationwide results (216 vs 219 seats) is actually quite close to the actual results (213 vs 219; 4 seats uncalled as of November 22, 2022), but my district-by-district results were not so accurate.
Prediction for the 2022 House Midterms
Introduction In this week’s blog, I present my final prediction model for the 2022 House Midterms. My final prediction model is a pooled linear regression model using data of almost all 435 districts from 1950-2020 to then predict for 2022 at the district level. I predict that the Democrats will win 216 seats, while the Republicans will win 219 seats, resulting in a Republican victory in the House of Representatives.
Blog 7: Shocks and Unexpected Events
Introduction This week, I learned about shocks and unexpected events and whether they have an effect on election outcomes. However, my main model for the week did not include shocks and unexpected events and instead focused on incorporating a pooled model. In my model, my dependent variable was Democratic two-party vote share and my independent variables were the average generic ballot score for Democrats, gdp percent difference between Q7 and Q8, incumbency, and the interaction between gdp and incumbency.
Blog 6: The Ground Game - Campaigns
Introduction This week, I explore the effects of voter turnout on the Democratic vote share and seat share at the Congressional district level. Working together with Lucy Ding and Kaela Ellis, we created models for all 435 Congressional districts (for the first time this semester!). A more extensive look at all of our combined work can be found in this presentation, which we presented in class on Tuesday, October 18 to GOV 1347.
Blog 5: The Air War - Advertisements
Introduction This week, I explored the effect of political advertisements on the Democratic vote share at the Congressional district level. Using political advertisement data from 2006-2018, I am able to run models for 152 congressional districts. Then, I specifically looked at Pennsylvania’s 10th district to make a model that includes both Democratic advertisement share (%) and Democratic generic ballot polling and to make a prediction for this district’s Democratic vote share in 2022.
Blog 4: Expert Predictions and Incumbency
Introduction: This week, I explored expert predictions and actual results of the 2018 Congressional elections at the district level. In addition, I explore incumbency as an independent variable for future models and predictions. 2018 Congressional Elections at the District Level The above maps represent the Democratic and Republican vote share for each U.S. congressional district during the 2018 elections. There are districts where the vote share for either party is 0 or 100 and this is because there were uncontested elections.
Blog 3: Polling
Introduction: This week, I focused on polling to help predict the 2022 House party seat share (%) for Democrats and Republicans. What Do Forecasters Do? FiveThirtyEight’s approach to forecasting congressional elections is as follows, “take lots of polls, perform various types of adjustments to them, and then blend them with other kinds of empirically useful indicators (what we sometimes call “the fundamentals”) to forecast each race. Then they account for the uncertainty in the forecast and simulate the election thousands of times” (Silver, 2022).
Blog 2: Economy and Elections
Introduction: This week, I focused on evaluating predictive models that used national economic variables as predictors for the incumbent party’s vote margin (%) in House congressional races. My goal was to better understand the economic model of voting behavior of congressional elections. Previous Literature: Achen and Bartels (2017) analyzed the economic model of voting behavior of presidential races. They found that, “it is possible to account for recent presidential election outcomes with a fair degree of precision solely on the basis of how long the incumbent party had been in power and how much real income growth voters experienced in the six months leading up to Election Day.
Blog 1: Introduction
Hello! My name is June Park and I am a junior at the college studying Government on the data science track and this is the beginning of my blog for GOV 1347: Election Analytics. Introduction: This week, I focused on visualization customization of congressional races. Map of Republican/Democrat Vote Share Margin by STATE (2016, 2018): The first set of maps represent the two-party vote share margin in the 2016 and 2018 congressional elections.