A RECENT poll which appeared to show a majority of Scots oppose independence has brought the “whole political polling industry into disrepute”, according to a leading Yes campaigner.

The Savanta ComRes research, published by the Scotland on Sunday paper, has led to a tangled web of claims and counter claims which look set to result in the firm behind the survey being reported to a polling watchdog. Questions also remain about why a key metric, which could have swung the result in favour of the Yes side, was omitted.

The poll recorded a majority of 52% for No when undecided voters were excluded. The Scotland on Sunday reported a “No vote lead as Salmond inquiry drives voters away from Scottish independence”. It was the first poll in 25 to show majority support for the Union.

But pollsters soon raised objections when they realised the figures were not weighted for voter turnout.

This is despite the firm’s last poll, in February, swinging from a Yes minority to a majority of 53% when the same weighting was applied.

Pressed for answers by pro-independence organisation Business for Scotland (BfS), Savanta ComRes political research director Chris Hopkins admitted that excluding the information was “unusual” and “not ideal’’ – though he denied there was anything “conspiratorial’’ about the decision.

He explained that the “likelihood of voting” weighting had been abandoned, in consultation with the Scotland on Sunday, because “we did not have the resources to do it within the timeframe”.

The polling boss pointed to a disclaimer in the Scotland on Sunday report which read: “These figures are not weighted for voter turnout, with further polling expected this week to show a clearer impact of the inquiry on Scottish independence voting intention. These figures on Scottish independence are not directly comparable with previous polls on the subject, due to this and the nature of the poll.”

But feeling that a series of questions remained unanswered, BfS chief executive Gordon MacIntyre-Kemp has vowed to write to the British Polling Council, a standards body for research firms, to demand an investigation.

READ MORE: Top political scientists question results of latest Scottish independence poll

Savanta ComRes had initially informed BfS that there were no plans to republish the poll figures with the standard methodology applied. When the entire data set from the research was released – as is required under British Polling Council rules – Hopkins told BfS that respondents had not even been asked about the likelihood of them voting. He said: “The question wasn’t asked purely because we knew we wouldn’t end up using it for weighting. That will mean it is not possible to retrospectively apply that weight.’’

Yet having seen the data, MacIntyre-Kemp was dubious about the accuracy of that response, leading to him lodging a complaint with the polling standards body. He said: “I can’t prove that they did ask the question and just left it out of the data they published but it looks highly suspicious. As a result we will be writing to the British Polling Council and asking them to investigate if Savanta ComRes has just published incomplete data that contradicts their statement that they did not ask the question, which in turn contradicts the earlier statement that suggested they did ask for intention to vote but just didn’t have time to apply the weighting.”

However, when The National made a further enquiry, Hopkins stated that respondents had been asked about the likelihood of them turning out to vote – the weighting just hadn’t been applied due to time and resource constraints.

Asked whether the figures could be republished with the key metric included, Hopkins said it was a decision for the Scotland on Sunday – the Sunday sister to its daily stablemate, the Scotsman.

MacIntyre-Kemp told The National last night: “How the Scotsman and Savanta ComRes behaved brings the whole political polling industry into disrepute. For me it’s about accuracy and informing people not manufacturing partisan stories.”

BfS, which has commissioned numerous independence polls, estimated that it would take between five and 10 minutes to apply the weighting to the results. Hopkins declined to comment on whether this was accurate, simply stating that his team did not have the resources to complete the process by the deadline set by the Scotland on Sunday.

Mark Diffley, a former Ipsos MORI director who now runs the Diffley Partnership, was one of several pollsters to raise questions about why the weighting had not been carried out. While stressing that he has no knowledge of possible resource or time constraints at Savanta ComRes, Diffley confirmed to The National that applying the weighting is “not a hugely complicated” process.

BfS noted that February’s poll – which produced raw data that was “almost identical” to Sunday’s poll – shifted from a No lead to a Yes lead once consideration was given to the likelihood of voting. Quizzed about this, Hopkins added: “We do not normally see this weighting having a major impact but for some reason it did so in that February poll.’’

The metric is just one of several mitigating factors considered by pollsters, including age, sex, location and past voting record. Yet voter turnout was the only weighting which was not applied.

It was the first time that Savanta ComRes had published results on an independence poll without this particular weighting included.

Commenting on the poll, Professor Sir John Curtice highlighted the “marked” effect that weighting the figures for voter turnout could have. He said 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.”