Public Policy Polling
Graded against the actual result across 302 races (from 637 polls, through 2024).
Head-to-head vs the VotePredictor model
The fair, apples-to-apples test: on the 300 races Public Policy Polling actually polled, how its final poll's margin compared to what the VotePredictor model predicted for those same races.
| Model | Avg miss (pts) | Called right |
|---|---|---|
| Public Policy Polling | 4.66 | 81% |
| VotePredictor | 3.93 | 86% |
VotePredictor aggregates all the pollsters, so it's expected to beat any single one on margin — that's the value of averaging. The honest comparison among forecasters is on the combined board.
Every race (300)
Each race Public Policy Polling polled, scored on its final poll — the call right before the vote — against the actual Dem−Rep result. Click a race for its full detail.
Accuracy by time to election
Lower is better. Time to election runs right (election week) to left (~2 months out).
By the numbers
| Time to election | Polls | Avg miss | vs field | Called right |
|---|---|---|---|---|
| ≤1 wk | 174 | 4.08 | -0.20 | 86% |
| 1–3 wk | 154 | 4.30 | -0.77 | 70% |
| 3–6 wk | 184 | 4.94 | -0.80 | 80% |
| 6–9 wk | 125 | 4.93 | -1.22 | 81% |
vs field is this pollster's average miss minus all pollsters' at the same lead time — green beats the field, redtrails it. Our historical polls reach ~2 months out; earlier polling isn't in the record.
Track record by cycle — getting better?
| Year | Polls | Avg miss | Lean (house effect) |
|---|---|---|---|
| 2008 | 84 | 3.8 | R+1.6 |
| 2009 | 9 | 5.8 | R+0.0 |
| 2010 | 96 | 5.6 | R+0.2 |
| 2011 | 9 | 6.7 | D+2.5 |
| 2012 | 203 | 3.5 | R+1.5 |
| 2013 | 7 | 8.9 | D+5.6 |
| 2014 | 83 | 5.3 | D+3.7 |
| 2016 | 52 | 4.5 | D+4.5 |
| 2018 | 24 | 3.8 | D+0.4 |
| 2020 | 50 | 6.3 | D+6.3 |
| 2022 | 12 | 3.6 | R+0.2 |
| 2024 | 5 | 3.0 | R+3.0 |
Do we credit a pollster for fixing its bias? Each cycle, the model re-estimates every pollster's lean from all its earlier polls (walk-forward) and subtracts it before using the poll. We tested weighting recent cycles more — it doesn't help: a pollster's lean in one cycle barely predicts the next (correlation 0.28), so the swings above are mostly noise, and averaging over more history beats chasing the latest cycle. The all-time estimate we use came out within ~0.5% of the best option.