Forecast update: 8 August 2014

Forecast b 140808

A very small uptick for the Conservatives in the polls this week: they’re up 1 point in the UK Polling Report average, with “others” down 1 and Labour, the Lib Dems and UKIP holding steady. It moves our forecast roughly back to where it was three weeks ago, undoing the gains Labour made the following week.

The Tories’ position as slight favourites to win the most seats has improved a touch: from 52-48 last week to 55-45 now. Their chances of winning a majority are up from 26% to 30%, though that’s still lower than at any point from when our model launched in October to June.

Our central forecast? A Hung Parliament with the Conservatives 23 seats short of a majority, winning 303 seats to Labour’s 292 and the Lib Dems’ 26. Again, that’s a small improvement for the Tories on the last couple of weeks, but still worse for them than any forecast until June. (As with last week’s central forecast, a Tory-Lib Dem coalition in this scenario would only have a very slim majority, while a Labour-Lib Dem one would not command one at all.)


Date of forecast: 8 August 2014
Days till the election: 272

Inputted current average poll shares (from UK Polling Report)
Con: 33%
Lab: 36%
LD: 8%
Others (inc. UKIP): 23%
– UKIP: 13%

Forecast Election Day Shares (with 95% Prediction Intervals)
Con: 36.0% (±7.4, i.e. 29% – 43%)
Lab: 32.1% (±5.6, i.e. 27% – 38%)
LD: 11.8% (±8.3, i.e. 4% – 20%)
Implied point estimate shares for:
– Others (inc. UKIP): 20.1%
– UKIP: 11.4%

Forecast Election Day Seats (with approximate 95% Prediction Intervals)
Con: 303 (223 – 395)
Lab: 292 (205 – 367)
LD: 26 (21 – 33)
(Prediction intervals assume LD & others shares at central forecast, Con & Lab shares vary as per prediction intervals)

Central forecast: Con largest party, but short of a majority by 23

Approximate probabilities of key outcomes
Con largest: 55%
… with a majority: 30%
Lab largest: 45%
… with a majority: 21%
Hung Parliament: 49%
… with Con largest: 26%
… with Lab largest: 23%
(probabilities may not sum due to rounding)

3 thoughts on “Forecast update: 8 August 2014”

  1. For future reference can you please explain how you use the UK Polling Report data. You say above that your input was 33/36/8 for the 3 main parties but UKPR were showing a weighted average of 32/36/8 for the whole of last week, the same figures you used for your 1st August update, until Monday morning this week, 3 days after the 8th August update. Do you get prior access to their weighted figure, or do you use the unweighted poll data, or was this week’s 33% a mistake ?

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s