Deltapoll Methodology

May 2026

The current Deltapoll polling methodology is based upon an online quota sample approach, which, combined with a number of technical interventions, seeks results that are representative of adults in Great Britain aged 18 and above as a whole.

Sampling

Deltapoll invites specific members of online panels to participate in each survey we undertake. Only those invited are allowed to take part. Exclusions are applied to ensure that nobody can participate on consecutive polls, unless one or more non-standard conditions applies (such as the need to draw very large sample sizes).

Quotas are applied to the following variables: gender, age and region.

Weighting

Data are weighted to a number of geo-demographic and voter-graphic variables. Data are weighted to match demographic population targets from reliable sources (ONS population estimates, National Readership Survey, Labour Force Survey, etc).

These weights are applied simultaneously by iterative proportional fitting, sometimes called rim-weighting or raking. Data are weighted to detailed targets based on intersections of age, gender, region, urban/rural classification, education, ethnicity, employment status, and personal income.

Estimating Party Support in Voting Intention Polls

Specifically for the polling of voting intention, exponentially weighted moving estimates are applied.

This method involves combining multiple waves of polling rather than only using the most recent. This is because polling with a sample size of around 2,000 inevitably leaves gaps or small samples for a number of major demographic groups.

This is done by combining data from multiple survey waves and then applying an exponential weight towards more recent waves. When applying rake weights, this allows the weight scheme to upweight a handful of respondents from previous waves who meet demographic deficits, without the overall representation of old data within the sample exceeding a certain (low) threshold.

The overall effect is that it becomes possible to weight to higher-resolution targets, including complex interactions of demographic variables, ensuring a balanced and representative sample even within specific regions, income brackets, age brackets, etc.

Estimating Turnout in Voting Intention Polls

When estimating turnout in voting intention polling, account is taken of varying reliability and meaning when respondents report their likelihood to vote.

British Election Study data is taken from before and after the 2024 election and logistic regression is used to model the effect of different demographics on whether respondents voted (declared after the election). Voting probability is then predicted for the demographic target groups, down-weighting based on vote likelihood.

Demographic targets are therefore representative of the expected population of voters, rather than the population as a whole.

This model is used to predict respondents’ true likelihood to vote based on a combination of their demographics and their self-reported likelihood to vote, and re-weight respondents’ voting intention based on this.

Data accuracy

With the exception of a ‘final’ poll published on the day of an election, any vote intention poll is a snapshot of opinion at that moment in time, not a prediction of a future event. Further, all polls are subject to a wide range of potential sources of error.

On the basis of the historical record of the polls at recent general elections, there is a 9 in 10 chance that the true value of a party’s support lies within 4 points of the estimates provided by an individual poll, and a 2 in 3 chance that they lie within 2 points. This is especially important to keep in mind when calculating party lead figures.

We continually review our methods, and may make further adjustments or changes to any aspect of our polling methodology at any point in time. Any such change would be reported with the full tables on the Deltapoll website.

For more information, please visit: https://deltapoll.co.uk/voting-intention