One Sentence Summary

Using the new historical election data, I construct a 3-year rolling-window own-party jacknife-vote-share feature in the election model and we see adjusted R squared increase from 0.067 to 0.098.

Outline

This markdown contains table 01s for elections with a new Election LM model. Here I make use of the new historical data from Rowan, which allows me to construct a rolling window feature for own party vote share. I am making use of a three year window looking back, and excluding the current election year. This is constructed at the house of representatives level as these have the most years.

  1. Table 01 Configuration 4 (using own-party-vote-share-jacknife in the election_lm) with updated Mturk features in the same model

NOTE In this table, to allow for as much data as possible, I am using the older 4-voter side-by-side MTurk features without quality control.

Definitions

Before jumping into regression output, I will put all definitions of important terms here:

  1. Vote-Share : In all tables below, when vote-share is a LHS variable this means the vote-share of a specific candidate election. I.e. how much of the total vote did a specific candidate get in their election.

  2. Own-Party-Vote-Share-Jacknife : This is a feature and computed as the “average vote share of my party in this states house of rep. election over the previous 3 years excluding the current”

Table 1 - Configuration 4

Replacing own_party_win_rate with own_party_vote_share_jacknife in the election lm. This now includes:

  1. Party (limited to Democrat vs. Republican)
  2. Rolling window Vote-share of the candidates own party

NOTE We see a significant increase in the coefficient on the election_lm from 0.067 to 0.098. Previous election models used the vote share over the entire period, and did not have a rolling window function.

Own Party Vote-share-Jacknife is computed as: “average vote share of my party in this states house of rep. election over the previous 3 years excluding the current”

Table 01 - Version 04 - Election Regressions
Fit measured in adjusted R squared and AUC
Model Configuration Election Outcome Vote Share
Adjusted R Squared ROC AUC Adjusted R squared
Single Variable Model
Election LM 0.0977 0.6803 0.0877
Lower 95% C.I. 0.0716 0.6496 0.0628
Upper 95% C.I. 0.1275 0.7111 0.1152
Sex 0.0034 0.5150 0.0047
0.0003 0.4916 0.0001
0.0096 0.5383 0.0130
Skine-Tone −0.0086 0.5422 −0.0044
−0.0035 0.5092 −0.0006
0.0187 0.5752 0.0287
MTurk Features 0.0154 0.5653 0.0008
0.0073 0.5321 −0.0017
0.0332 0.5986 0.0128
P_hat_cnn 0.0988 0.6837 0.0770
0.0731 0.6529 0.0527
0.1275 0.7144 0.1046
Combined Variable Model
Election LM + P_hat_cnn 0.1883 0.7546 0.1598
0.1575 0.7267 0.1307
0.2222 0.7824 0.1925
Election LM + Sex 0.1001 0.6835 0.0923
0.0750 0.6529 0.0694
0.1288 0.7142 0.1225
Election LM + Sex + P_hat_cnn 0.1900 0.7563 0.1634
0.1587 0.7286 0.1357
0.2265 0.7841 0.1986
Election LM + Sex + Skin-Tone 0.0920 0.6907 0.0869
0.0809 0.6603 0.0779
0.1399 0.7212 0.1310
Election LM + Sex + Skin-Tone + P_hat_cnn 0.1832 0.7604 0.1593
0.1650 0.7329 0.1432
0.2335 0.7879 0.2104
Election LM + Sex + Skin-Tone + MTurk 0.1036 0.7048 0.0856
0.0932 0.6749 0.0767
0.1540 0.7348 0.1369
Election LM + Sex + Skin-Tone + MTurk + P_hat_cnn 0.1866 0.7656 0.1568
0.1678 0.7382 0.1442
0.2377 0.7929 0.2118