Misconceptions About Online Polling

Web polls are inadequate. Anyone can take part and skew the sample.

There’s no comparison. “Quick polls” or “instant web polls” that take a snapshot of responses are neither scientific nor descriptive of any particular population. These polls may elicit a response (and come front-loaded with tenuous disclaimers) but their value is dubious and bears little resemblance to a representative survey.

The polls we conduct include a detailed methodology and we always itemize the number of interviews, dates as well as the margin of error. The only time we enlist quick polls are as a means to recruit new panel members to the Angus Reid Forum. These results are never reported to the public.

Online surveys use “convenience sampling”

Convenience sampling refers to how some firms recruit on the basis of proximity to the researchers or product or other element that could be defined as ‘convenient.’ In the same realm is survey-specific advertising, which allows panel members to self-select to participate in any given survey. Quality market research panels never rely on these substandard techniques.

An online panel does not allow for random selection

Other critics claim that online polling is biased because people choose to become panelists in order to respond to surveys themselves. This, instead of being picked at random through a list of telephone numbers. It’s an erroneous argument that assumes every person will be asked to take part in every online poll, every time. Conversely, invitations for particular surveys are sent to a randomly selected portion of the Angus Reid Forum to ensure a representative sample.