Abstract
SUMMARY A classification of sources of error in opinion polling is presented, and related to investigations of observed error in the polls at the time of the 1992 general election. This leads directly to implications for reducing the potential for error in future. It is argued that quota sampling bias, incorporating both selection bias and unit non-response bias, is a major source of error. The adoption of probability sampling methods is proposed as a way to reduce this bias, and pollsters and their clients are encouraged to experiment with such methods. An example of a practical probability sampling design is described. Other sources of error which have been identified, and for which methodological improvement is suggested, are the treatment of item refusals, the treatment of those who say they 'don't know' for whom they will vote and the treatment of respondents' predictions of whether they will vote.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have