I expect that many of you will be pleased to learn that a new Welsh Political Barometer opinion poll is on the way. First results from the new poll will be published next Monday, June 29th. This will be the first opinion poll conducted in Wales since the general election. As has been our established practice, the poll will include voting intention figures for both the National Assembly and Westminster, as well as for EU membership and Income Tax Devolution referendums. And they will be a few other delights as well.
That will be fun, won’t it?
Before we publish any findings, however, I thought it would be appropriate to offer a brief word about methodology. After their not-entirely-satisfactory experience in the general election, all the main pollsters have been reviewing their methods. (For a useful discussion of the first public meeting of the British Polling Council’s Inquiry into the performance of the opinion polls at the general election, see Anthony Wells’ excellent overview here). Some of the pollsters, in their GB-wide polls, have already implemented significant methodology changes since the election.
Our friends in YouGov have not yet completed their own internal investigations and considerations as to what changes might be necessary. The methodology of the new Barometer poll will therefore be largely unchanged from their pre-election polls in Wales, with one fairly small exception. In the words of Adam McDonnell, a Research Executive at YouGov who has worked with us on this poll:
“Currently, while we work out our new sampling frames and weighting, we are using the same sampling methods as pre-election and the same weight variables with the exception of Party Identification. Instead of Party Identification we are weighting by 2015 general election result.”
Given that the final YouGov Welsh poll was actually very accurate – only being about one percentage point too low for the Conservatives and one point too high for Labour, with the other parties being estimated very accurately indeed – these changes should not make much difference to the results. They should probably tend to reduce Labour’s reported support very slightly compared with the pre-election methodology, and increase that of the Conservatives by a tiny amount, while leaving that of the other parties pretty much unchanged.
Therefore, if we see in our new poll any substantial changes in reported support levels for the parties (when compared with our previous YouGov polls in Wales), then those shifts will not be ones that can simply be accounted for by methodological changes. Shifts in party support might reflect normal sampling variation between individual polls, or they might reflect genuine changes in the public mood. But methodological changes by YouGov would not be responsible. I hope this clarifies how we should respond to next week’s poll.
(By the way, in case you are wondering – at time of writing this I have not seen any results from the poll. So I am not trying to offer tantalising hints of what the findings are. I can’t do that because I don’t know – and nor does anyone else yet either!)