THE bombshell poll which suggested a majority of Scots now support remaining in the Union would have shown the opposite had standard methodology been used, a top pollster has suggested.

The poll, published by Scotland on Sunday, the stablemate of the Scotsman daily newspaper, reported a “No vote lead as Salmond inquiry drives voters away from Scottish independence”.

This poll, conducted by Savanta ComRes, purported to show a majority of 52% for No when Don’t Knows are excluded.

However, Professor Sir John Curtice, a leading political analyst and the president of the British Polling Council, suggested that it would have shown a lead for Yes had standard methodology been used.

READ MORE: Poll showing Yes support down should be 'treated with caution'

Reports on the poll said it had found 46% support for No, 43% support for Yes and 10% for Don't Know.

But those figures were not weighted for voter turnout, with the Scotland on Sunday paper saying further polling was “expected this week”.

Pollster Mark McGeoghegan said: “You cannot take the difference between two polls to be reflective of real-world change, never mind assign a reason to that change, if you've changed the weighting. Don't compare incomparable polls.”

Britain Elects, a poll aggregator, removed the poll’s results from their tracker, citing the “curious decision” to publish the non-turnout weighted figures.

The aggregator said: “Last night we tweeted (and now deleted) a commissioned poll on Scottish independence.

“This survey, with Yes at 43% and No at 46% came with a key caveat: ‘These figures are not weighted for voter turnout’ and ‘are not directly comparable with previous polls on the subject’.

"As such, this survey will not feature in the Britain Elects poll tracker. Curious decision for a publication to run the non-turnout weighted figures."

Mark Diffley, a former Ipsos MORI director who now runs The Diffley Partnership, said: “I don’t get why it wasn’t filtered for turnout - it’s straightforward to do and ‘further polling out this week’ does not seem to be a reason not to do it.”

Commenting on the Savanta ComRes poll, Curtice highlighted the "marked" effect that weighting the figures for voter turnout could have.

He said that the most recent results were “unchanged from equivalent figures” found by the same polling firm in early February, adding: “Turnout weighting had a particularly marked impact in that poll.”

When turnout weighting was applied to those same figures in the February poll, it found a 53% lead for Yes (with Don’t Knows excluded).

Curtis said: “So the Savanta ComRes poll confirms a drop in support for Yes in #indyref2 vote intentions that was already evident [from highs of 58%], but not that the recent coverage of the #Salmond inquiry has had any further impact.”

The National:

He added that the drop in support for Yes and the SNP since the beginning of 2021 seemed to be about more than the harassment complaints inquiry.

A second poll on Scottish independence, conducted by Panelbase, was published today in the Sunday Times. This poll found that 46% of Scots would back Yes and 47% No. A total of 7% of people answered Don’t Know.

No mention was made in the article of how the results would look with Don’t Know’s excluded, but standard turnout weighting was used.

Curtice said that this Panelbase poll, with Don’t Knows excluded, records an even 50/50 split between the Yes and No side.

He said that the difference in percentages disappeared when Don’t Knows are excluded because “just two-three more people said No than Yes!”. He added that the same had happened with the recent Survation poll published in the Daily Record.

Curtice’s analysis of the Panelbase poll predicted that the SNP would take 65 seats in Holyrood in May’s election, leaving them with a majority of a single seat in the 129-member parliament.

James Kelly, who runs the ScotGoesPop blog, tweeted: "An extraordinary weekend when the media misled the public about the polls - the ComRes poll wasn't real, and the Panelbase poll showed 50-50, not a No lead: the TWENTY-SIXTH consecutive poll to show Yes on 50% or higher."