You are on the Natcen site

Click here for Scotcen

natcen map

You are on the Natcen site

Click here for Scotcen

natcen map

Public opinion on the EU referendum question

An experimental approach using a probability-based online and telephone panel

Bf86eb19f5314d6e9afdcd3072e4c465 1462442634
Researchers: Martin Wood
Published: August 2016

Our unique survey of voting intentions in the EU referendum suggested that the outcome of the referendum was on a knife-edge and was likely to fall in between the divergent outcomes being anticipated by phone and online polls.

  • New approach finds 53% for remain, 47% for leave.
  • A vote of 50% each was within the survey’s statistical margin of error, which meant that even leaving aside the possibility of a late swing, our results suggested that a majority vote for Leave shouldn't be ruled out.

You can download the full report, Public opinion on the EU referendum question: a new approach.

We are also making the survey's microdata available, find out more by scrolling down this page.

Background to the report 

NatCen developed a new and experimental approach to measuring public opinion, which addressed some of the points raised by the inquiry into the 2015 General Election Polls.

The panel was conducted both over the internet and by phone with a randomly selected sample of respondents, the first time that a randomly selected panel has been established in Britain.

The panel has been designed to maximise methodological rigour and has three distinctive features that set it apart:

  • The panel is the first ‘random probability’ online and telephone panel in the UK. Panel members were recruited via the 2015 British Social Attitudes (BSA) survey whose participants were selected at random and interviewed in a high quality face-to-face approach. Unlike most online panels, a random probability panel is not formed from people who have ‘volunteered’ to be a member.
  • Those who failed to respond to the survey over the internet have, where possible, been followed up by telephone.
  • The survey has been conducted over an extended period of 4 weeks (May 16th to June 12th 2016) and has made multiple attempts to reach hard to contact panel members.

This survey has been self-funded with the purpose of contributing to the methodological debate around opinion polls in the EU Referendum.

Publication of survey microdata

The General Election 2015 Polling Inquiry highlighted the lack of transparency around methods used to adjust for turnout.

In the spirit of the Polling Inquiry, we are making the micro-data available for our survey, so that researchers and analysts can test their own approaches.

Find out more about the microdata

For more information read our technical information document,  and to request the data, please email

This data set includes all the substantive variables, non-response weights, turnout weights and other administrative variables . We have also included explanatory variables from the British Social Attitudes survey, from which our panel members were originally recruited.

Download the report

Download microdata technical information

  • Our panel

    Find out more about our online and telephone probability panel. 

    Read more