Scott Rasmussen (Rasmussen Reports)
Graded against the actual result across 372 races (from 1072 polls, through 2012).
Head-to-head vs the VotePredictor model
The fair, apples-to-apples test: on the 303 races Scott Rasmussen (Rasmussen Reports) 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 |
|---|---|---|
| Scott Rasmussen (Rasmussen Reports) | 4.68 | 91% |
| VotePredictor | 3.40 | 95% |
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 (370)
Each race Scott Rasmussen (Rasmussen Reports) 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 | 116 | 3.82 | -0.46 | 75% |
| 1–3 wk | 344 | 4.91 | -0.16 | 80% |
| 3–6 wk | 398 | 4.80 | -0.94 | 81% |
| 6–9 wk | 214 | 6.36 | +0.21 | 79% |
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 | 101 | 5.1 | R+3.3 |
| 2004 | 103 | 2.9 | D+0.6 |
| 2005 | 10 | 4.7 | R+4.6 |
| 2006 | 140 | 4.2 | R+1.9 |
| 2008 | 263 | 5.3 | R+3.0 |
| 2009 | 11 | 4.5 | D+3.0 |
| 2010 | 281 | 6.0 | R+2.3 |
| 2012 | 161 | 5.0 | R+4.0 |
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.