The British Election Study is pleased to announce the release of the fifth wave of the Internet Panel. You can download the data here.
In total 30,725 respondents took wave 5 of the British Election Study. 28,073 of these also took wave 4, an overall wave on wave retention rate of 89.6%. 17,673 respondents took all of the first five waves of the survey, 58.5% of respondents who originally took wave 1. Wave 5 was conducted by YouGov between 31st March 2015 and 6th May 2015.
The combined waves 1-5 BES Internet Panel dataset can be downloaded here.
The British Election Study 2015 is managed via a consortium of the University of Manchester, The University of Oxford, and The University of Nottingham. The Scientific Leadership Team is comprised of Professors Ed Fieldhouse, Jane Green, Hermann Schmitt, Geoff Evans and Cees van der Eijk. The team is supported by researchers Dr Jon Mellon and Chris Prosser, and also by BES 2015 consultant Professor John Curtice (University of Strathclyde).
1 Weights and samples
Around 30,000 respondents were interviewed in each wave (referred to as the full sample). However, we also define a smaller core sample of around 21,000 respondents in each wave that constitute a cross-sectional group which is more representative than the full sample (i.e. the range of weights is smaller than in the full sample). For cross-sectional work, where you wish to say something about the proportion of the population giving a certain response, we recommend using this core sample.
As before, we provide two cross-sectional weights for each wave, the full weight (e.g wt_full_W5) that covers all respondents who took the wave 5 survey and the core weight that weights a smaller more representative sample of respondents (wt_core_W5). The panel dataset includes a cumulative weight that covers respondents who have taken all waves so far in the study (wt_full_W1W2W3W4W5) as well as a pre-campaign to campaign weight (wt_full_W4W5).
All of these weights are constructed at the regional level (i.e. Scotland, England, Wales and London are weighted separately to population values) and then adjusted to account for the oversampling of Scottish and Welsh voters.
2 Campaign Wave
The campaign wave (wave 5) was conducted as a daily survey with a subsample of respondents invited to complete the survey on each day of the election campaign. There are two variables which record which day of the campaign a respondent completed the survey – CampaignDayW5, which is the numeric day of the campaign period and enddateW5, which is a formatted date variable. There is also a daily weight variable (wt_daily_W5).
Due to a technical error the party contact questions were not asked of those respondents who took the survey during the first weeks of the campaign. It was asked of respondents who took the survey on and after April 24th.
The party like-dislike scale for the SNP was originally only asked to Scottish respondents, but from day 29 it was asked to all respondents (‘likeSNPExtraW5).
3 Most Important Issue coding
We are also releasing categorized responses to the “most important issue” facing the country question for all waves. These responses were categorized using an automated process described here.