Pages

ICM/Guardian Vote intention poll | 11th July 2016

The latest vote intention figures include a number of methodological changes that have been in the pipeline for some time, but needed the reinforcement of a successful outing at the EU referendum before full confidence in them could be established. Given momentous events at Westminster with today’s news that Theresa May is the sole politician left standing in the Conservative’s leadership race (and that the changes had little impact compared to last week’s more pre-changes publication), it seems as good a time as any to introduce them now, allowing an ICM benchmark to be set at the outset of Theresa May’s likely leadership of the party.
In summary, the ICM vote intention numbers are based on the following:
  1. The release of email invites staggered over a weekend in order to prevent certain types of respondent bed blocking geo-demographic quotas (introduced pre-referendum).
  2. Additional quotas set on voting in the 2015 General Election, allowing for DK/Refusal contributions (introduced late 2015).
  3. Past vote weighting to the 2015 result. The impact of this is negligible, given the application of political quotas as stated in (2) immediately above.
  4. Replacement of the traditional turnout modelling scheme based on the 1-10 probability of actually voting in General Elections. This scheme is no longer fit for purpose in an age of overstating turnout, both in total and relative terms. Instead, ICM has constructed a turnout probability matrix cross-referencing age and social grade, modelled to 2015 actual turnout levels via estimates from various sources, including the British Election Studies (New).
  5. The introduction of political interest weighting, also based on BES numbers (New).
  6. Partial refuser and total refuser post-survey adjustment, both introduced after the 2015 General Election.

The combined impact of these changes is small, compared to this poll but based on last week’s methods, or indeed last week’s pre-change poll but based these methods applied. As a rough guide, the impact is to add 1-point to the Conservatives, while taking off 1-point from Labour.
The voting figures are:
Conservatives 38%
Labour 30%
Lib Dems 8%
UKIP 15%
SNP 5%
Green 4%
Other *%