This document contains two new tables which build off the configuration 3 table from previous updates. These new configurations (4 and 5) include:
vote_share instead of a parties win-record in a particular state in all other yearsvote_share_ratio of the individuals own/opponent partyReplacing win_rate with vote_share in the election lm. This now includes:
Vote-share is computed as: “average vote share of my party in this state over all years excluding the current”
| Table 01 - Version 04 - Election Regressions | ||
|---|---|---|
| Fit measured in adjusted R squared and AUC | ||
| Model Configuration | Adjusted R Squared | ROC AUC |
| Single Variable Model | ||
| Election LM | 0.0108 | 0.5728622 |
| Lower 95% C.I. | 0.0023 | 0.5376222 |
| Upper 95% C.I. | 0.0255 | 0.6081021 |
| Sex | 0.0153 | 0.5604767 |
| 0.0047 | 0.5314525 | |
| 0.0315 | 0.5895009 | |
| Skine-Tone | −0.0049 | 0.5454082 |
| −0.0013 | 0.5106945 | |
| 0.0252 | 0.5801219 | |
| MTurk Features | 0.0017 | 0.5433649 |
| −0.0016 | 0.5077725 | |
| 0.0153 | 0.5789574 | |
| P_hat_cnn | 0.0972 | 0.6814615 |
| 0.0675 | 0.6487163 | |
| 0.1294 | 0.7142067 | |
| Combined Variable Model | ||
| Election LM + P_hat_cnn | 0.1044 | 0.6861957 |
| 0.0755 | 0.6536344 | |
| 0.1388 | 0.7187569 | |
| Election LM + Sex | 0.0229 | 0.5967729 |
| 0.0091 | 0.5618596 | |
| 0.0418 | 0.6316862 | |
| Election LM + Sex + P_hat_cnn | 0.1065 | 0.6888393 |
| 0.0803 | 0.6563431 | |
| 0.1421 | 0.7213355 | |
| Election LM + Sex + Skin-Tone | 0.0173 | 0.6147882 |
| 0.0164 | 0.5801846 | |
| 0.0572 | 0.6493917 | |
| Election LM + Sex + Skin-Tone + P_hat_cnn | 0.1023 | 0.7019433 |
| 0.0868 | 0.6699021 | |
| 0.1563 | 0.7339845 | |
| Election LM + Sex + Skin-Tone + MTurk | 0.0179 | 0.6196128 |
| 0.0191 | 0.5851869 | |
| 0.0627 | 0.6540388 | |
| Election LM + Sex + Skin-Tone + MTurk + P_hat_cnn | 0.1032 | 0.7052443 |
| 0.0945 | 0.6733634 | |
| 0.1628 | 0.7371253 | |
Replacing win_rate with vote_share_ratio in the election lm. This now includes:
Vote share ratio is computed as: “average vote share of my party in this state over all years excluding the current / opponents parties vote share in this state over all years excluding the current”. This works as we are limiting ourselves to races with two parties !
| Table 01 - Version 05 - Election Regressions | ||
|---|---|---|
| Fit measured in adjusted R squared and AUC | ||
| Model Configuration | Adjusted R Squared | ROC AUC |
| Single Variable Model | ||
| Election LM | 0.0104 | 0.5718189 |
| Lower 95% C.I. | 0.0022 | 0.5365509 |
| Upper 95% C.I. | 0.0250 | 0.6070869 |
| Sex | 0.0153 | 0.5604767 |
| 0.0049 | 0.5314525 | |
| 0.0309 | 0.5895009 | |
| Skine-Tone | −0.0049 | 0.5454082 |
| −0.0009 | 0.5106945 | |
| 0.0267 | 0.5801219 | |
| MTurk Features | 0.0017 | 0.5433649 |
| −0.0014 | 0.5077725 | |
| 0.0157 | 0.5789574 | |
| P_hat_cnn | 0.0972 | 0.6814615 |
| 0.0695 | 0.6487163 | |
| 0.1289 | 0.7142067 | |
| Combined Variable Model | ||
| Election LM + P_hat_cnn | 0.1038 | 0.6856720 |
| 0.0760 | 0.6531037 | |
| 0.1378 | 0.7182404 | |
| Election LM + Sex | 0.0225 | 0.5969973 |
| 0.0096 | 0.5620844 | |
| 0.0418 | 0.6319102 | |
| Election LM + Sex + P_hat_cnn | 0.1059 | 0.6885440 |
| 0.0781 | 0.6560338 | |
| 0.1391 | 0.7210542 | |
| Election LM + Sex + Skin-Tone | 0.0170 | 0.6164495 |
| 0.0172 | 0.5818997 | |
| 0.0582 | 0.6509994 | |
| Election LM + Sex + Skin-Tone + P_hat_cnn | 0.1018 | 0.7012661 |
| 0.0896 | 0.6691915 | |
| 0.1534 | 0.7333407 | |
| Election LM + Sex + Skin-Tone + MTurk | 0.0177 | 0.6186759 |
| 0.0188 | 0.5842512 | |
| 0.0646 | 0.6531005 | |
| Election LM + Sex + Skin-Tone + MTurk + P_hat_cnn | 0.1028 | 0.7051144 |
| 0.0936 | 0.6732405 | |
| 0.1572 | 0.7369884 | |