Results of Clarke’s survey have no scientific credibility accuracy, or reliability

Fri Feb 27, 2015

Editor: In the Tuesday, February 24, 2015 edition of this newspaper, Andrew T. Clarke reported the preliminary results of a public opinion survey he conducted regarding the construction of Argyle International Airport that is based on questionable methodology (“A government’s dream: the Argyle International Airport. Success or failure?”, pp. 17, 23). For such a survey to be credible, reliable, and accurate it must answer “yes” to at least two questions:{{more}}

First, was it based on a random sample of the Vincentian population? Given that several of the questions in the survey have a strong political component, a random sample needed to be drawn from the adult voting population in such a way that every voter has an equal chance of being selected to answer the questionnaire. Since there is not a single word on methodology in his summary of the findings — an absolute prerequisite in this kind of research — I can only assume that he did not select a random sample.

Second, was the sample of respondents big enough to make the results statistically representative of all voters? The 74 people who completed questionnaires make up less than 0.01 percent of the approximately 78,000 population of voters, 200 times below the two percent that is the minimum required in this kind of survey research.

Since the answer to both questions is “no,” the results of the survey have no scientific credibility, accuracy, or reliability.

It is more than a little ironic that a study investigating “the methodologies employed by large-scale projects in Third World countries” should be so methodologically flawed.

Hymie Rubenstein, Ph.D.

Professor of Anthropology (retired)

University of Manitoba

Winnipeg, Canada