My model: 88%
Wrong in Florida, North Carolina, Michigan, Wisconsin, Pennsylvania, and Ohio,
My personal prediction: 90%
Wrong in Florida, North Carolina, Michigan, Wisconsin, Pennsylvania,
Five Thirty Eight: (taken on Saturday) 92%
Wrong in Nevada, Michigan, Wisconsin, Pennsylvania
Five Thirty Eight Final: 88%
Five Thirty Eight Final: 88%
Wrong in Florida, Michigan, Wisconsin, Pennsylvania, North Carolina
Princeton Election Consortium: (taken on Saturday) 90%
Wrong in Florida, North Carolina, Michigan, Wisconsin, and Pennsylvania
Note: there was no call in Iowa on Saturday, but the final call was a Trump win so I am considering that call correct. The final call is identical
New York Times Upshot- 90%
Wrong in Florida, North Carolina, Michigan, Wisconsin, and Pennsylvania
Upshot did not have a final prediction.
Upshot did not have a final prediction.
Real Clear Politics (Both final and Saturday) 88%
Wrong in Florida, Nevada, Michigan, Wisconsin, New Hampshire, and Pennsylvania
I also ran my model for 2008 and 2012 and it matched the Five Thirty Eight predictions for the winners. I was 93.58% as accurate as Five Thirty at predicting means (using root mean square error).
I also ran my model for 2008 and 2012 and it matched the Five Thirty Eight predictions for the winners. I was 93.58% as accurate as Five Thirty at predicting means (using root mean square error).
Considering the success of other models, I did relatively well. The core ideas behind my project appear to be solid. My predictions were highly competitive with compared to models created by organizations that had far more resources than I did. I look forward to 2018, where I plan to predict the senate races.
This will be the final blog post. I will continue posting about statistics in our everyday lives at balexanderstatistics.com
This will be the final blog post. I will continue posting about statistics in our everyday lives at balexanderstatistics.com
Note that the 93.58% number compares my average root mean square error for all three elections to 538's which only predicted the mean in 2012 and 2016.
ReplyDelete