The full tables for Angus Reid’s first UK voting intention poll are now up here, so we can have a dig around. From the top, the sample is drawn from an online panel of paid volunteers, in much the same way as YouGov.

The survey asks voting intention using the question “If a General Election were held tomorrow, which one of the following parties would you be most likely to support in your constituency?”. This refers specifically to how people will vote in their own constituencies, in the hope that it will pick up some tactical voting. To be honest, I doubt it will make a massive difference (my theory is that the reason it does so in the PoliticsHome marginal poll is specifically because people are asked the question both ways).

Respondents are prompted by just the main parties, if they say “other” they are given a second question to find which “other” party they would support. I had pondered whether the high level of other support was the result of including smaller parties in the prompt, but that is not the case (I can see no obvious reason why Angus Reid found support for “other” parties so much higher than other pollsters – recently ICM have had them at 10%, Populus 12%, YouGov 12%, ComRes 13%, MORI 11%. AngusReid have them at 17%. I guess time will tell if there’s something methodological causing it, or it’s just a blip.)

Respondents who say don’t know are then given a “squeeze question”, in the way Ipsos-MORI and ComRes do, asking them which party they are leaning towards. This had virtually no effect on the final figures, switching them from 41/23/20 to 40/23/20.

Like YouGov, there is no filtering or weighting by likelihood to vote. This is something that should in theory help Labour – filtering by turnout normally increases the reported Conservative vote, since their supporters invariably say they are more likely to vote. However, our only real point of comparison is the only regular UK online pollster, YouGov – they don’t filter by likelihood to vote, and it doesn’t seem to produce figures that are kinder to Labour. As I’ve suggested before, perhaps its because the lack of an interviewer effect means people are happier to say they won’t vote if they really won’t, or perhaps the sort of people who don’t vote don’t join internet panels.

Finally we get to the question of weighting. AngusReid are weighting by the normal demographics, plus newspaper readership, and by recalled 2005 vote. There is no adjustment for false recall – they weight to the actual shares of the vote in 2005, which they have found to work in the past in Canada (where they do indeed have a good record).

Intuitively this may seem right… but no other UK pollsters do it because of false recall. Evidence from panel studies shows that people do not accurately report their past voting. There are various explanations for this: people are embarrassed to say they didn’t bother to vote, so give the party they would have voted for; people who voted tactically give their first preference, rather than the party they put an X next too; people saying the party they wish they’d voted for with hindsight. Whatever the reasons, there is broad concensus amongst British pollsters that false recall means more people claim to have voted Labour than actually did, and invariably fewer people report having voted Lib Dem than actually did. I discuss it at (slightly) greater length here.

The lessons pollsters draw from this are different – ICM, Populus and ComRes adjust their past vote weighting targets to account for false recall. MORI take the view that false recall makes past vote entirely unsuitable for weighting. Putting aside the theory, here’s what it means in practice. Below is the recalled 2005 past vote from the pollsters who provide it (YouGov weight by party ID instead so we cannot compare to them). I’ve also shown it repercentaged to exclude the don’t knows and won’t votes.

ICM: CON 19%, LAB 23%, LDEM 13%, Others 5%, DNV 32%, Ref & DK 8%.
Repercentaged – CON 33%, LAB 38%, LDEM 22%

Populus: CON 19%, LAB 22%, LDEM 12%, Others 5%, DNV 35%, Ref & DK 7%
Repercentaged – CON 33%, LAB 38%, LDEM 21%

ComRes: CON 18%, LAB 21%, LDEM 12%, Others 5%, DNV 35%, Ref & DK 10%
Repercentaged – CON 32%, LAB 38%, LDEM 21%

Ipsos MORI: CON 20%, LAB 28%, LDEM 10%, Others 6%, DNV 27%, Ref & DK 10%
Repercentaged – CON 32%, LAB 43%, LDEM 16%

Angus Reid: CON 25%, LAB 26%, LDEM 17%, Others 5%, DNV 26%, Ref & DK n/a
Repercentaged – CON 34%, LAB 36%, LDEM 23%

As you can see ICM, Populus and ComRes have very close figures indeed. MORI do not weight by past vote, and hence their sample has a much higher proportion of people saying they voted Labour in 2005 (though without weighting by these figures, MORI’s past vote figures to vary from month to month). Evidently Angus Reid are weighting Labour to a lower level of support than the other pollsters, and weighting the Liberal Democrats and Conservatives to a higher level.

The figures aren’t necessarily directly comparable, since we don’t know whether there is the same level of false recall in a telephone survey using live interviewers, and an internet survey with no interviewer effect – for example, if some of false recall is a social desirability bias against admitting to not voting, it may be smaller when people are asked online. Prima facie though we should expect their figures to show a lower level of Labour support and a higher level of support for the Liberal Democrats than some of their rivals. Whether that happens in reality, of course, remains to be seen.

13 Responses to “More on the Angus Reid poll”

  1. Anthony , see my comment on the previous thread on the number of people in this survey who said they voted “Other” in 2005 .
    Populus past vote weightings changed this month from 19/23/13 to 19/22/12 . Earlier in the year they messed about completely and used 13/16/9 , a very strange experiment .

  2. Populus’s target weights will move over time as their estimates of false recall change. As I understand it they don’t weight to integers, so the targets have probably moved from 22.6 to 22.4 or something like that, rather than a sudden step change. (ICM’s targets will change in the same way, but too a lesser degree)

    Populus say they didn’t change their weighting at all earlier this year. It appeared to be something very odd with DNVs or Don’t knows, that was never really pinned down.

  3. Anthony,

    Would I be right in believing that if we take actual result / turnout for 2005, the figures were roughly:

    Con – 20%
    Lab – 22%
    LD – 14%
    Others – 5%
    Did not vote – 40%

    Your repercentages show that Angus Reid, apart from slightly overstating Cons, are closest to the actual result.

  4. Anthony,

    Angus Reid recall figures also show much lower levels of DNV.

    This may of course be down to there having been a higher turnout among internet users (consistent with low turnout among lower socio-economic demograhics) which in turn explains why they may be picking up lower levels of past Lab support than otehr pollsters.

    If I recall correctly, the supposed prolLab bias in teh current boundaries has far more to do with there having been much lower turnouts in Lab’s urban heartlands in 2001 and 2005 than actual boundaries. This again is consistent with the findings above for Angus Reid’s past recall.

    In summary, I suspect that Angus Reid have understated underlying Labour support in this poll, but that it might actually be a better reflector of how the eventual figures come out once differential turnout has been taken into account.

    What implications that has for seats won / lost is anyone’s guess.

  5. It’s an interesting result and also little bit predictable for me. Thanks for updating us every day.

  6. Paul H-J,

    I haven’t worked them out, but that should be the case since Angus-Reid are weighting to those figures.

    (Whether your’s a “right” is harder to say than you’d think, because of the DNV figure. We know how many people on the electoral register in 2005 did not vote, but we don’t know how many people there were not on the register. Nor do we know how many people on the register who didn’t vote were actually people on the register twice, or people who were actually dead.)

  7. Thanks Anthony – a very good post.

    Having been close to this project for some time I was a little surprised when I first heard that the past vote weighting was to the actual 2005 result.

    This is, of course, an online survey from members of a polling panel who are getting paid and I buy the argument that you cannot assume that the approach of the phone pollsters is necessarily applicable.

    AR’s Canadian experience is relevant and we’ll probably have to wait until the May 8th to find out whether this is correct or not.

    Whatever I think it is a good thing that there is another pollster doing it in a different way and it’s great that Politcalbetting has been part of it.

  8. “YouGov – they don’t filter by likelihood to vote, and it doesn’t seem to produce figures that are kinder to Labour.”

    That is not what it looks like recently. YouGov seem very kind ot Labour as are ComRes.

  9. your last post, anthony, highlighted a query i had about the DNV’s-

    do any of the polsters ask a suplimentary question to find out WHY people did not vote? For people like myself who were not on the electoral registar at the time [i turned 18 a month after the GE; how annoying!]- do any polsters ask a question along the lines of ‘who would you have voted for if you were given the chance’ ? or would that just be taking things too far…

  10. Craig H – some do offer the alternative answer of “Too young”, but since they will also ask age as part of the normal demographic questions, it’s not that necessary. If someone gives their age as 19, it goes without saying that they didn’t vote in the last general election.

    Past vote is mostly asked only for weighting purposes, so there would be no purpose in asking how people who weren’t eligible would have voted.

  11. Looks like the economy is still contracting (-0.4% last quarter) which fits with my monetarist analysis of the government response: quantitative easing is staving off a massive deflationary crisis as a result of the contraction in the money supply, but with the PSBR in chaos real interest rates are still too high to enable a recovery. “Cyclical” fisical policy on the part of the government won’t just fail to stimulate the economy, but by increasing the budget deficit it will further choke the recovery.

    Until a government is suicidal enough to try to increase lending by reducing the deficit, Britain will not have a stable recovery. This is why I think Labour’s chances of an economic recovery by the next election now look extremely bleak.

  12. “(I can see no obvious reason why Angus Reid found support for “other” parties so much higher than other pollsters – recently ICM have had them at 10%, Populus 12%, YouGov 12%, ComRes 13%, MORI 11%. AngusReid have them at 17%. I guess time will tell if there’s something methodological causing it, or it’s just a blip.)”

    Why on earth would you say that?
    Obviously if the question is asked then some people will be willing and able to answer it.
    This prejudice towards other parties – just presenting an option of “Others” is arguably one factor that keeps them down in polls.

    Angus Reid is no dummy, and I find his figures far more plausible than the lower ones… it is logically fallacious to draw a conclusion that several polls producing similarly low figures are more likely to be correct simply because there are more of them; the methodology, as you suggest, matters – though not necessarily in the way you seem to have assumed.

    Moreover, there’s a plausible case for Others being up in the polls, what with recent events still playing out in a way that would not seem to be favourable towards the three largest parties.

  13. Oh well, nobody bit.