Political polling hit record levels in 2009

The number of published opinion polls into British general election voting intention hit a twenty plus year high in 2009 with 141 polls carried out during the calendar year.

That is the highest figure since at least 1987 (when my records commence)* and more that completes the polling industry’s recovery from its post-1992 nadir. You can see the quarterly trend in this graph:

Number of opinion polls per quarter

(Click on image for large version)

As I explained previously:

The 1992 general election was a bad one for the British political polling industry. During the campaign, the vast majority of polls put Labour ahead and of the final round of polls three put Labour ahead, one put Labour and the Conservatives neck-and-neck and only one – Gallup – gave the Conservatives a lead, but even that was a mere 0.5%. The actual result? A Conservative lead of 7.6%.

The response of the polling industry was a series of post-mortems and experiments with changes in methodology. Amongst those who commissioned polls, though, the response was also one of greater scepticism of the value of commissioning polls. Add in first the economic pressures of the 1990s and then the widespread seemingly inevitability of a Labour general election victory after Tony Blair become Labour leader, and it is no surprise that during the 1992-97 Parliament the number of opinion polls was consistently lower than in 1987-1992.

The prospect of an election more keenly contested than any since 1992, the declining cost of polling (thanks to phone and then internet polling) and the wider range of outlets commissioning polls (including in 2009 Political Betting) has resulted in the bumper year of polls.

Whether politics or political commentary is the better for this is another matter, particularly when you bear in mind that the standard margin of error on polls is +/- 3 percent. A sequence of two polls, one showing a party one percent higher than the previous really tells very little about any actual possible change in party support because the two margins of error overlap so heavily.

That’s a point often lost in commentary where changes well within that overlap are breathlessly described as party support rising, nose-diving, shifting and responding to events.

But of the 141 polls across 2010, for example, only 13 showed a statistically significant shift** in Conservative support from the previous poll by the same pollster and only 16 showed such a shift for Labour. Just 11 showed a statistically significant shift in Liberal Democrat support.

Headlines along the lines of “Sorry, no news from our latest poll as the changes are all too small to be statistically significant” though are not exactly common.

As the number of polls looked at grows, conclusions can be drawn with more confidence about changes in party support which would not be significant if they were present in only one poll. But that requires reports to put polls in their proper context alongside other recent polls, something with the traditional media is still very poor at. Hopefully 2010 will see that become the norm with the traditional media starting to catch up on the standards of political poll reporting which are common across political bloggers.

* Although there are many records of public opinion polls published before then, none that I’ve found provide enough information across all the polling companies to replicate this information in earlier years even when combining difference sources. It’s therefore more likely true that these are the highest figures ‘since records began’ :-) … but if you know otherwise, do let me know.

** Although an individual poll is usually statistically significant to +/-3% (assuming no systematic errors), for the change between two polls to be statistically significant it has to be greater than approximately 4.7%. That is because, for example, if a party’s support has stayed static at 35%, the first poll may show the party to be at 33% and the second at 37% – an increase of 4% which does not actually signify a statistically significant shift. An explanation of the maths is here.

Read more by or more about .
This entry was posted in Polls.
Bookmark the web address for this page or use the short url http://ldv.org.uk/17401 for Twitter and emails.
Advert

3 Comments

One Trackback

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.

If you are a member of the party, you can have the Lib Dem Logo appear next to your comments to show this. You must be registered for our forum and can then login on this public site with the same username and password.

Your email is never published. Required fields are marked *

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

Advert



Recent Comments

  • User AvatarJohn Roffey 27th May - 10:36am
    Caron Lindsay 27th May '15 - 8:11am "How can anyone possibly say with confidence that we would have retained 30-40 seats if Nick hadn’t been...
  • User AvatarSimon Hebditch 27th May - 10:12am
    Of course, there is a real problem with right/left definitions and relevance in the modern world. But the problem also exists in terms of defining...
  • User AvatarJohn Roffey 27th May - 10:10am
    Neale Upstone 27th May '15 - 9:40am "However, are you really suggesting we abandon the idea of meeting in person? That’s the last thing our...
  • User Avatarpeter tyzack 27th May - 10:09am
    The Preamble to our constitution defines who we are, and who should be members. Anyone who supports the preamble should be part of our movement,...
  • User AvatarJohn Roffey 27th May - 9:57am
    I don't know if all of your suggestions are possible [simple ignorance] - but there is no doubt in my mind that the Party needs...
  • User AvatarAdrian 27th May - 9:49am
    David-1 27th May ’15 – 12:52am "The idea that there is some sort of opposition between “equality of opportunity” and “equality of outcomes” is absurd....
Wed 27th May 2015
Thu 28th May 2015
Fri 29th May 2015
19:30
Sat 30th May 2015
Sun 31st May 2015
Mon 1st Jun 2015
Tue 2nd Jun 2015
Wed 3rd Jun 2015
Thu 4th Jun 2015
Fri 5th Jun 2015
Sat 6th Jun 2015
Tue 9th Jun 2015
Wed 10th Jun 2015
Thu 11th Jun 2015
19:00
Fri 12th Jun 2015
Sat 13th Jun 2015
Wed 17th Jun 2015
Thu 18th Jun 2015
Sat 20th Jun 2015
Sun 21st Jun 2015