Public Opinion Strategies
Graded against the actual result across 162 races (from 207 polls, through 2022).
Head-to-head vs the VotePredictor model
The fair, apples-to-apples test: on the 140 races Public Opinion Strategies 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 Opinion Strategies | 6.88 | 68% |
| VotePredictor | 4.27 | 79% |
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 (162)
Each race Public Opinion Strategies 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 | 11 | 4.61 | +0.33 | 64% |
| 1–3 wk | 62 | 5.20 | +0.13 | 66% |
| 3–6 wk | 94 | 6.30 | +0.56 | 64% |
| 6–9 wk | 40 | 9.17 | +3.02 | 73% |
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) |
|---|---|---|---|
| 1998 | 3 | 5.4 | R+5.4 |
| 2000 | 5 | 5.7 | R+3.9 |
| 2002 | 22 | 5.6 | R+0.2 |
| 2004 | 17 | 5.8 | R+1.9 |
| 2006 | 21 | 10.6 | R+9.7 |
| 2008 | 27 | 6.3 | R+5.2 |
| 2010 | 34 | 5.7 | R+0.4 |
| 2012 | 34 | 6.4 | R+5.7 |
| 2014 | 15 | 4.9 | D+1.0 |
| 2016 | 14 | 7.6 | D+4.0 |
| 2018 | 7 | 5.0 | R+4.6 |
| 2020 | 5 | 4.5 | D+2.2 |
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.