The election is over, but work to improve opinion polling is not

Jane Frost, CEO at the Market Research Society, examines the performance of the polling industry in the 2024 UK general election.

Palace of Westminster

Amid the flurry of announcements, appointments, briefings and the King’s Speech, there’s been little time post the election for the new government to do anything other than buckle down and look ahead. For the social and market research sector, however, now that the dust has settled, we have an opportunity to reflect on the performance of our opinion polls leading up to 4th July.

By and large, when the constituency results came in, the polls were seen to get it right with uniform predictions of a Labour landslide. This was in no small part due to the hard work of our sector and the nuanced research conducted ahead of polling day. 

The election campaign saw an explosion of multilevel regression and post-stratification models, better known as MRPs, which became the acronym of the six-week campaign. The use of additional insights and demographic data potentially helped pollsters better reflect the subtleties of our electoral landscape. 

Also welcomed was the more considered approach to media reporting on the opinion polls than we’ve seen in previous election years. Few headlines glaringly misinterpreted the forecasts. Perhaps it was the complexity of the MRPs that, rather than confusing journalists, as some feared, led them to interrogate the data more thoroughly and present it with greater care.

As part of this, some reporters were right to spot the disparity in the size of the Labour victory forecasted, and we must reflect on improvements to MRPs that may be needed over the next few months. The last nine MRPs conducted before polling day suggested that the party would hold between 426 and 517 seats once counting was complete. The upper estimates were some way off the 412 actually gained.

As the media and public pointed out, there were peculiarities within this election which will have contributed to the differing estimations – including the higher than usual number of voters who remained undecided until polling day. That said, the research sector shouldn’t be lulled into complacency – the results also reflect a wider history of the polls overestimating Labour support and underestimating that of the Conservatives. As ever, we need to think hard about how we can do better next time.

Part of the reason for the divergence was the difference in the MRP models built by each polling organisation. Different data sets were prioritised by each pollster – so it goes without saying that they came to varying conclusions. 

As the media, public and our sector get to grips with MRPs, we need to make sure their methodologies are communicated more effectively.

This partly comes down to transparency. Pollsters need to be open about the way they build their models for the public to truly make sense of them – and to understand how much store to put in the snapshots of the electorate they provide. It is about clarity and expectation management.

It is also about inclusivity. The polling sector has some ground to make up on diversity and inclusion, and we need to view it as the business critical issue it is. More diversity of experience in the opinion research sector will naturally trickle down into more representative research. If we don’t reflect the population that we seek to represent, how can we realistically expect to do our jobs accurately?

So I am delighted to give a belated but full-hearted welcome to the new president of the British Polling Council, Professor Jane Green, who I know shares many of my views on the issue of inclusivity in this part of the sector. I look forward to our future collaborations.

There’s plenty of room for optimism following the election. Fundamentally, the MRPs conducted over the course of the campaign brought more attention to the research sector, helping to showcase it as a dynamic and innovative place to work. Under the new government, we must keep up that momentum – and strive to do even better when the next vote is called. 

Jane Frost is CEO at the Market Research Society 

We hope you enjoyed this article.
Research Live is published by MRS.

The Market Research Society (MRS) exists to promote and protect the research sector, showcasing how research delivers impact for businesses and government.

Members of MRS enjoy many benefits including tailoured policy guidance, discounts on training and conferences, and access to member-only content.

For example, there's an archive of winning case studies from over a decade of MRS Awards.

Find out more about the benefits of joining MRS here.

0 Comments

Display name

Email

Join the discussion

Newsletter
Stay connected with the latest insights and trends...
Sign Up
Latest From MRS

Our latest training courses

Our new 2025 training programme is now launched as part of the development offered within the MRS Global Insight Academy

See all training

Specialist conferences

Our one-day conferences cover topics including CX and UX, Semiotics, B2B, Finance, AI and Leaders' Forums.

See all conferences

MRS reports on AI

MRS has published a three-part series on how generative AI is impacting the research sector, including synthetic respondents and challenges to adoption.

See the reports

Progress faster...
with MRS 
membership

Mentoring

CPD/recognition

Webinars

Codeline

Discounts