For the fourth straight week, the favourite has changed in our forecast. Having fallen behind Labour last week, the Tories have retaken a slight lead, with a 51% chance of winning the most seats to Labour’s 49%.

The chances of a hung parliament have dropped slightly since last week’s high of 57%, but it’s still a bit more likely than either party securing a majority, with a 55% chance.

The Tories have gained a point in our polling average, to 32%, while UKIP and the Lib Dems have lost a point each and Labour remains on 34% for the third week running.

As a result, our central forecast now has the Conservatives winning 34.6% of the vote to Labour’s 31.4%, enough to give David Cameron’s party just three seats more than Ed Miliband’s: 298 to 295. In that hung parliament scenario, the Tories would be 28 seats short of a majority – which is also the number of seats the Lib Dems are forecast to win.

Date of forecast: 24 October 2014
Days till the election: 195

Inputted current average poll shares
Con: 32%
Lab: 34%
LD: 8%
Others (inc. UKIP): 26%
– UKIP: 16%

Forecast Election Day Shares (with 95% Prediction Intervals)
Con: 34.7% (±6.9, i.e. 28% – 42%)
Lab: 31.4% (±5.2, i.e. 26% – 37%)
LD: 11.2% (±7.2, i.e. 4% – 18%)
Implied point estimate shares for:
– Others (inc. UKIP): 22.7%
– UKIP: 14.0%

Forecast Election Day Seats (with approximate 95% Prediction Intervals)
Con: 298 (223 – 382)
Lab: 295 (214 – 365)
LD: 28 (23 – 34)
(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 28

Approximate probabilities of key outcomes
Con largest: 51%
… with a majority: 24%
Lab largest: 49%
… with a majority: 21%
Hung Parliament: 55%
… with Con largest: 28%
… with Lab largest: 27%
(probabilities may not sum due to rounding)