Response from Carolyn O'Keefe President MQO Research on the Poll

Well we now have part of the response from the MQO Research Company.

Now we can start to put in perspective what the polls value is.

As all the questions have not been answered I will ask again for further information.

First - Here is a statement from a report lead by Stanford University Researchers.

While the random-sample surveys were “consistently highly accurate,” the Internet surveys based on self-selected or “opt-in” panels “were always less accurate, on average, than probability sample surveys, and were less consistent in their level of accuracy,” the researchers said. Further, they said, adjusting these samples to known population values had no effect on accuracy (and in one case even worsened it) as often as that process, known as weighting, improved it.

The inconsistency is a challenge because it means the accuracy of one measure from an opt-in panel survey can’t reliably be taken to mean that other measures are accurate, the researchers noted. And there are other problems: While results of one of the seven opt-in online panels was “strikingly and unusually inaccurate,” they said, “the rest were roughly equivalently inaccurate,” suggesting that no one or another of these producers can claim to have perfected the approach.

One ABC reporter said:

The results shouldn’t be a surprise; as I’ve reported previously, non-probability samples lack the theoretical underpinning on which valid and reliable survey research is based; our policy at ABC News, as at several other national news organizations (including The Associated Press, The New York Times and The Washington Post) is not to report them.
The poll conducted by MQO was one of these polls. Although Ms. O`Keefe says the poll is a probability based one. This is not exactly accurate as it is a panel. This poll is not scientific (under the definition under MRIA) and may be very inacurate. You will note that Ms. O`Keefe does not say it is scientific. That is something she should have answered.

Further the MRIA - the Association MQO is a member of - public information states:

Online survey participants are self-selected, meaning that a margin of sampling error cannot be calculated or quoted for online panel research studies. Using margin of sampling error to describe the accuracy of online polling is misleading, and prohibited under MRIA’s Code of Conduct.

Does this mean that adding some phone panel participants in the midst of online polling makes this one different.

Below is what Ms. Carolyn O`Keefe provided me on the poll. As not all the information requested was NOT included - I will ask again for complete information.

I would be pleased to respond to your request. Please find attached a release outlining the methodology employed for the poll. The poll was paid for by MQO Research, it was not commissioned by any outside organization. I designed the questions for the survey.

The survey conducted was quantitative in nature, not qualitative research, so Questions 5-7 do not apply.

The poll was conducted through iView Atlantic, a proprietary research panel developed by MQO Research. This panel consists of over 12,000 Atlantic Canadians who have agreed to provide their opinions on Atlantic, provincial and local topics that matter to them. To ensure the representativeness of all Atlantic Canadians, iView Atlantic also includes a component of phone-based membership to reflect those Atlantic households who still spend limited time in an online environment. iView Atlantic is unique from other opt-in online panels in that panellists are recruited randomly by telephone, and indicate their preferred method of contact (either by phone or online).This means that individuals without Internet access are recruited and can participate in our panel surveys therefore enabling coverage of the entire population. iView Atlantic is a probability-based panel, meaning that every member of the population has an equal chance of being selected for participation.

The poll was based on a sample of 464 Newfoundlanders and Labradorians, with a margin of error of +/- 4.6%.  It was conducted between Wednesday, September 28 and Friday September 30, 2011.   The respondents were weighted regionally to ensure proper representation of the province as a whole.