VotePredictor
← All pollsters

Los Angeles Times

Graded against the actual result across 27 races (from 35 polls, through 2008).

Races polled
27
Polls
35
Avg miss
5.83 pts
Most recent
2008

Head-to-head vs the VotePredictor model

The fair, apples-to-apples test: on the 16 races Los Angeles Times actually polled, how its final poll's margin compared to what the VotePredictor model predicted for those same races.

ModelAvg miss (pts)Called right
Los Angeles Times4.0281%
VotePredictor1.97100%

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 (27)

Each race Los Angeles Times 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
2008 FL PresidentD+9.0D+2.86.2
2008 OH PresidentD+5.0D+4.60.4
2008 US PresidentD+8.0D+7.40.6
2006 CA GovernorR+17.0R+17.00.0
2006 CA SenateD+18.0D+24.46.4
2006 MO SenateR+3.0D+2.35.3
2006 NJ SenateD+4.0D+16.012.0
2006 OH SenateD+8.0D+12.34.3
2006 TN SenateR+5.0R+2.72.3
2006 VA SenateD+3.0D+0.42.6
2004 CA PresidentD+17.0D+9.97.1
2004 FL PresidentR+8.0R+5.03.0
2004 OH PresidentD+6.0R+2.18.1
2004 PA PresidentEVEND+2.52.5
2004 US PresidentR+1.0R+2.41.4
2004 CA SenateD+22.0D+19.92.1
2003 CA GovernorR+8.0R+17.19.1
2002 CA GovernorD+9.0D+4.94.1
2000 CA PresidentD+7.0D+11.84.8
2000 FL PresidentR+4.0EVEN4.0
2000 MI PresidentD+4.0D+5.11.1
2000 PA PresidentR+2.0D+4.26.2
2000 US PresidentR+6.0D+0.56.5
2000 CA SenateD+25.0D+19.35.7
1998 CA GovernorD+11.0D+19.68.6
1998 CA-46 HouseD+14.0D+17.13.1
1998 CA SenateD+5.0D+10.05.0

Accuracy by time to election

24686–9 wk3–6 wk1–3 wk≤1 wkavg miss (pts)
Los Angeles TimesAll 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 wk234.75-0.3283%
3–6 wk104.97-0.7780%

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)
199848.0R+8.0
200064.7R+2.8
2003320.4D+20.4
200493.5D+1.3
200674.7R+4.0
200842.1D+1.4

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.