McCrindle said that: “In the early years… when releasing internal, unpaid research, the methodology line referring to the number of people surveyed would sometimes record the number of people sent the survey rather than the number of surveys completed.

“Almost two years ago this was recognised by us to be inadequate and erroneous and since then we have only made reference to the number of completed surveys received.”

The company also said it had “inadvertently” used the term ‘representative’ to describe its online research panel in the past.

The correction document bears many similarities to the text of an earlier letter of apology – obtained and published by ABC – that was reportedly sent to clients. In this later document the company expresses “regret” for the misuse of ‘representative’ and for the “misconception” its sample wording created.

Media Watch devoted a nine-minute segment of its 17 October programme to three surveys McCrindle carried out which it alleged were based on sample sizes much smaller than those claimed by the company.

A company spokesman told Research: “The Media Watch segment covered historical issues and made misrepresentations of our research methodology based on misleadingly presented material from 2008 and 2009…The issues are unrelated to any of our commissioned research and findings.”

Despite reports that the Australian Market and Social Research Society (AMSRS) was conducting an investigation into the claims made by Media Watch, the McCrindle spokesman said: “We have not been contacted by the AMSRS nor advised of any inquiry based on the Media Watch segment.”