Sir John Curtis: Can we trust opinion polls that predict Tory ‘defeat’?

Image source, Getty Images

  • author, Sir John Curtis
  • Role, Professor of Politics at the University of Strathclyde

Three recent opinion polls predicted that the Labor Party was on track to win a large majority in the general elections.

So, are the Conservatives really on track to “wipe” the election? Or should we be skeptical of the poll results?

First, what do old-style opinion polls – those that typically interview 1 to 2,000 people in order to estimate parties’ share of the vote across Britain as a whole – tell us?

At least 16 companies have conducted at least one survey in the seven days since Monday of last week.

In those polls, Labor’s average support was 41%, three points lower than when Rishi Sunak called the election.

But they are still 20 points ahead of the Conservatives, who are now on 21% – also three points lower than they were at the start of the campaign.

According to these regular polls, the Prime Minister’s campaign has had no success in reducing Labour’s lead.

The party that has made gains is the Reform Party in the United Kingdom.

Since Nigel Farage declared himself leader and is running as a candidate, support for reform has risen by five points compared to the start of the campaign.

The Liberal Democrats also rose slightly – now at 11% – with a one-point increase on the campaign trail. Meanwhile, the Green Party maintains the 6% it started with.

First, only 62% of people said they would vote either Conservative or Labour.

That would be a record low since Labor first became the Conservatives’ main challenger in 1922.

Second, the Conservative Party has never been so low in the polls – including, at least during a general election.

MRP “megapolls”

But what about those polls that predicted a large, and in some cases very large, majority for the Labor Party?

The latest three are from polling firms YouGov, Savanta and More in Common and use what is called a multilevel regression and stratification (MRP) model.

They usually interview a much larger number of voters, in some cases as many as 40,000.

Because they interview many people, they can see how those with different demographic characteristics — such as gender, age, and educational background — are likely to distribute their support between parties.

Meanwhile, sources like the Census tell us how many people in each demographic group live in each electoral district.

By combining these two data sources, statisticians can estimate how many people are likely to vote for each party in each electoral district.

As a result, these MRP polls give us an idea of ​​how different the ups and downs of party support have been across the country since the last election. Under our electoral system, this difference can play a major role in determining how many seats each party wins.

However, their estimates of the number of Conservative MPs who would be returned ranged widely, from 53 to 155.

So why are all the estimates so low? Why are they so different?

All these polls suggest that the Conservatives are losing support more in the constituencies they are trying to defend than in seats that are already in opposition hands.

If this happens on the Fourth of July, the Conservatives will lose many more seats than they would if their support fell by about the same amount everywhere.

However, MRP polls do not agree on the extent to which the Conservative vote has fallen in the seats they currently hold.

For example, More in Common estimates that in constituencies where, in 2019, the Conservatives were 25 points or more ahead of the second-placed Labor candidate, the Tory vote is now down on average By 23 points.

In contrast, in seats where Labor finished first and the Conservatives second last time, they believe Conservative support has fallen by 12 points – 11 points lower.

“Safer seats”

However, in their poll, which suggested the Conservatives might win at least 53 seats, Savanta and Electoral Calculus estimated the difference between the two types of seats in the average decline in Conservative support at 21 points.

Their poll suggests that support for the Conservatives fell on average by up to 33 points in their safest seats.

But there is good reason to believe that such a pattern will emerge.

On average, support for the Conservatives is currently 24 points lower than in 2019 in regular UK-wide opinion polls. However, the party won less than 24% of the vote in 2019 in as many as 100 seats – so, if the polls are right, Conservative support is certain to decline further elsewhere.

Meanwhile, the Reform UK Party’s predecessor, the Brexit Party, did not contest seats held by the Conservatives in 2019. This time the party stands in most of the seats held by the Conservatives. This means that her lead, achieved largely by winning one in four Tory voters in 2019, is now strongest in such seats – largely to the Conservatives’ expense.

But how big is the potential decline in Tory support? No one can be sure. But the fate of many Tory MPs may depend on what the answer may be.

Sir John Curtis is Professor of Politics at the University of Strathclyde, and a Senior Fellow at the National Center for Social Research and the United Kingdom in a Changing Europe. He also co-hosts the Trendy podcast.

Leave a Reply

Your email address will not be published. Required fields are marked *