VotePredictor
← All pollsters

The Polling Company Inc.

Graded against the actual result across 26 races (from 31 polls, through 2018).

Races polled
26
Polls
31
Avg miss
6.15 pts
Most recent
2018

Head-to-head vs the VotePredictor model

The fair, apples-to-apples test: on the 25 races The Polling Company Inc. actually polled, how its final poll's margin compared to what the VotePredictor model predicted for those same races.

ModelAvg miss (pts)Called right
The Polling Company Inc.6.0880%
VotePredictor5.1984%

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 (25)

Each race The Polling Company Inc. 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.

RaceTheir callResultMissCall
2018 IA-1 HouseD+2.0D+5.13.1
2018 NY-22 HouseR+8.0D+2.310.3
2018 MO SenateR+3.0R+5.82.8
2018 WV SenateD+4.0D+3.30.7
2017 VA GovernorD+1.0D+8.97.9
2016 IA-1 HouseR+11.0R+7.73.3
2014 AZ GovernorR+7.0R+11.84.8
2014 IA-1 HouseR+1.0R+2.31.3
2014 IA-4 HouseR+13.0R+23.310.3
2014 VA-10 HouseR+16.0R+16.10.1
2014 OR SenateD+8.0D+18.910.9
2012 IN GovernorR+9.0R+2.96.1
2006 AZ-5 HouseR+9.0D+4.013.0
2006 CO-7 HouseD+5.0D+12.97.9
2006 CT-4 HouseR+10.0R+3.46.6
2006 GA-8 HouseR+1.0D+1.12.1
2006 IN-8 HouseD+12.0D+22.010.0
2006 KY-4 HouseR+4.0R+8.34.3
2006 OH-6 HouseD+18.0D+24.26.2
2006 PA-6 HouseD+1.0R+1.32.3
2006 TX-17 HouseD+12.0D+17.85.8
2006 MO SenateD+9.0D+2.36.7
2006 MT SenateD+9.0D+0.98.1
2006 NJ SenateEVEND+16.016.0
2006 PA SenateD+16.0D+17.41.4

Accuracy by time to election

24686–9 wk3–6 wk1–3 wk≤1 wkavg miss (pts)
The Polling Company Inc.All pollsters (field average)

Lower is better. Time to election runs right (election week) to left (~2 months out).

By the numbers

Time to electionPollsAvg missvs fieldCalled right
1–3 wk54.66-0.4180%
3–6 wk226.10+0.3677%

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?

YearPollsAvg missLean (house effect)
2006137.0R+3.6
201474.8D+1.4
201739.3R+9.3
201854.2R+2.8

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.