Gallup
Graded against the actual result across 38 races (from 120 polls, through 2012).
Head-to-head vs the VotePredictor model
The fair, apples-to-apples test: on the 29 races Gallup 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 |
|---|---|---|
| Gallup | 3.96 | 76% |
| VotePredictor | 2.57 | 93% |
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 (38)
Each race Gallup 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 | 29 | 3.73 | -0.55 | 59% |
| 1–3 wk | 22 | 4.56 | -0.51 | 64% |
| 3–6 wk | 44 | 3.77 | -1.97 | 66% |
| 6–9 wk | 25 | 6.24 | +0.09 | 64% |
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) |
|---|---|---|---|
| 2000 | 20 | 4.8 | R+1.7 |
| 2002 | 7 | 2.9 | R+1.7 |
| 2004 | 44 | 4.4 | R+1.0 |
| 2006 | 15 | 4.3 | D+0.3 |
| 2008 | 22 | 4.8 | R+3.7 |
| 2012 | 10 | 3.9 | R+3.6 |
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.