When up is down and down is up

A quick explanation for people who are new to pouring over the details of polls and, as several people have commented, are confused by the conflicting figures given for whether a party is up or down and if so by how much in a poll.

Different polling companies use different methods, so comparing – say – an ICM poll with a previous BPIX poll isn’t comparing like with like. Therefore when looking at a poll it makes sense to calculate up/down figures based on the previous poll by that polling firm.

However, polling firms often do work for more than one media outlet and media outlets (still) prefer to compare poll results with the previous poll that they commissioned and not with the previous poll from that firm.

For example, suppose the Lib Dems get 28% in an ICM poll for The Guardian, then 26% in an ICM for the Sunday Telegraph and then 27%  in another Guardian ICM poll. The Guardian will report that third poll as showing the Lib Dems falling by one point (28 to 27), whilst most commentators – such as Mike Smithson and Anthony Wells – will, more sensibly report it as +1 (26 to 27).

The Guardian is in fact one of the best news outlets which it comes to revealing the existence of other polls by its pollster that were published in rival newspapers. It often will give both figures, though use the “Guardian only” comparison in its main graphic. Nearly all the other media outlets don’t even go that far and simply ignore those other polls.

That’s why therefore you sometimes get the same poll reported in different places and in different tweets with varying +/- figures. (If you are a regular on Twitter, watch out for Tweetminster who as far as I’ve seen normally give the media style figures – ignore any intervening rival polls – as they tweet the ‘official’ media figures.)

Just for some extra complication there are occasionally two polls from the same firm with overlapping fieldwork dates, raising a question about which of those was the “first” poll; in addition, sometimes pollsters vary from their usual methodology – raising the question of whether that change is big enough to mean a like for like comparison should ignore the poll with the different methodology. Those are very much the rare cases however; nearly all the variation is explained by the main point above.

Read more by or more about , or .
This entry was posted in Polls.


  • Andrew Suffield 3rd May '10 - 12:54pm

    And that’s before you account for accuracy. Most polls are what, about +/- 3%?

  • paul barker 3rd May '10 - 3:56pm

    Theres a new poll of Lab/Con marginals, both Libcon & PolBet have links to it. The most interesting finding is that 1 in 6 voters are still thinking of switching to us, a number that seems to be holdin up as the Election nears. Even a third of these would make us the largest Party in votes. There is still everything to play for.

  • Actually, it makes sense to look at trend accross all the polls, rather even than see if a party is up or down.

    Take today ipsos-mori poll of marginals – Cons +1, Lab -2 Lib Dem -1, given the margin of error, it might as well be no change.

    Also Ipsos mroi say : “However, given that national polls are suggesting the Conservatives are more likely to lose seats to the Liberal Democrats than gain from them, this majority is not necessarily guaranteed. ”

    Hmm, not the bit reported in the papers. Nor is it clear how if the Cons and Lab are tied at 36% each in key marginals, that means the conservatives will win them all ! A bit of commonsense suggetss that for each one where the Cons are above 36% there will be others where they are on less than 36%

  • There is some distinctly funny business going on with polls from normally reliable and respectable polling organisations.

    Mike Smithson, who has looked at the detailed figures coming out of the ICM May 2nd poll, finds that ICM’s adjustment for Don’t Knows has little impact on CON and LD projected shares of the vote but buffers the LAB share. While the published result showed LAB on 28 and LD on 28 the unadjusted figure, which did not adjust for Don’t Knows, was LD 28.3 and LAB 25.6 with the CON on 33.6.

    I wonder if Don’t Know – taking into account previous Labour voting behaviour – is more like Don’t Bother or ‘not Labour this time’.

    On the basis of the canvassing I have been doing over the past fortnight my hunch is that previously LAB…but don’t know now… is closer to either ‘sod the lot of them’ or ‘I’m seriously thinking of changing’.

    As I understand it ICM isn’t the only outfit that is adjusting to take account of surprisingly low scores for LAB.

    I strongly agree with Mouse about the latest MORI marginals poll. The reporting of the poll – including by Reuters who commissioned it – is atrocious.

    It is a poll based on a sample of just over 1000 in 57 Labour held seats. No fine grain detail about trends in different regions is available for a poll of that kind. A collapse in the Labour vote in some marginals seats and a dramatic Tory advance in others is just as likely as a uniform swing against Labour. Reuters really should be doing better in reporting the poll they commissioned – instead of which these psephological illiterates are reporting that their poll “suggests the Conservative Party could now be on course for a majority of around two seats in the 650-seat House of Commons”.

Post a Comment

Lib Dem Voice welcomes comments from everyone but we ask you to be polite, to be on topic and to be who you say you are. You can read our comments policy in full here. Please respect it and all readers of the site.

To have your photo next to your comment please signup your email address with Gravatar.

Your email is never published. Required fields are marked *

Please complete the name of this site, Liberal Democrat ...?


Recent Comments

  • Steve Trevethan
    Might we be facing two problems at the same time, which may or maybe not significantly connected? One is increasing poverty and the other is increasing inflati...
  • Steve Trevethan
    Might it be the case that the attitudes and performance of the Metropolitan Police in this matter come somewhere on a continuum/spectrum between inept and corru...
  • Paul Barker
    I used to support the idea of local Pacts with The Greens (GPEW only) but there would be long-term consequences that would be bad for both Parties. Labour may e...
  • Tristan Ward
    Since Compass is aligned to the Labour Party whose interest is in beating Liberal Democrats, it is doubtful whether any recommendations made by Compass are in t...
  • Jenny Barnes
    "The unemployment rate for January to March 2022 decreased by 0.3 percentage points on the quarter to 3.7%. For the first time since records began, there are fe...