Monday 12 November 2018

Tapping into a nation's mood to give a voice to the public

Ken Walshe of Quantum Research explains the methodology behind the scientific telephone polls conducted on behalf of the 'Sunday Independent'

The Sunday Independent Quantum Research polls use a dedicated team of methodologists, researchers, and analysts, who share psychology, survey research data analysis, market research, sociology and political qualifications and experience, to deliver quantitative and qualitative results.

The team is deployed on a rapid response model, conducting these polls within the shortest time to print, on questions compiled by the editorial team of the Sunday Independent newspaper.

The Quantum Research Survey Team completes 500 telephone surveys among a random sample of telephone users.

The panel are pulled at random and their responses are broken down according to demographic and gender specifications. When contacted to solicit involvement and response, respondents have no prior knowledge of the subject matter of the study, and are free to choose not to participate.

Each survey is personally administered through standard interview techniques and controls are in place to ensure that no participant has the opportunity to respond more than one time in any given poll.

All sample surveys and polls, irrespective of methodology or sampling techniques, are subject to multiple sources of error, which are most often not possible to quantify or estimate, including sampling error, coverage error, error associated with non-responses, error associated with question wording and response options, as well as post-survey weighting and adjustments.

Achieving 100 per cent accuracy is impossible and, at best, theoretical, because no published polls, irrespective of methodology or sample size, come close to this ideal position.

The most significant difference between an open access poll, such as those used on television, radio phone-ins and online surveys, and the Sunday Independent Quantum Research poll, is that open access polls have self-selected participants, while scientific polls typically randomly select their samples. Popular web polls attract whoever wishes to participate, those with agendas or special interests, and are entirely appropriate for certain situations.

The reason the Sunday Independent has chosen to use a random scientific sample of the population is to prevent influence by single-interest groups and lobbyists.

Quantum Research conducts telephone polls on behalf of the Sunday Independent to give a voice and representation to the general public. It is not just limited to the readers and/or subscribers of the newspaper.

In practice, our survey team need to balance the cost of a large sample against the reduction in sampling error.

therefore, a sample size of around 500 is used and would be a typical compromise for a political survey.

This decision has been balanced by the commitment to repeat the survey on a high-frequency basis, monthly, to ensure reproducibility and repeatability of results and trends, and to make sure that the results continually reflect changing circumstances such as, for example, economic prosperity.

The Sunday Independent Quantum Research polls appreciate the willingness of the public to co-operate in our surveys, and your responses allow the Sunday Independent to tap into public opinion and provide clear trends on how you feel the country is being run and managed.

The decision to participate may be correlated with traits that affect the study, making the participants a non-representative sample.

Notably, people who have strong positions or substantial background, experience or knowledge, may be more willing to spend time answering a survey than those who do not. The Sunday Independent tracks this through analysis of the "Don't knows" and, to minimise the effect, asks the same set of questions over a period of time, in order to track changes in opinion, and show repeatability and trending in the results.

Editor's Choice

Also in Irish News