Quality indicators
Main quality elements: accuracy, relevance, coherence.
Measurement error is the difference between measured values and true values. It consists of bias (systematic error introduced where the measuring instrument is inaccurate this error remains constant across survey replications) and variance (random fluctuations between measurements which, with repeated samples, would cancel each other out). Sources of measurement error are the survey instrument, mode of data collection, respondent's information system, respondent, and interviewer.
A description of the processes developed to reduce measurement error associated with the survey instrument and to optimize the comparability of the data being collected should be made available. This will indicate to users the accuracy and reliability of the measures as well as the coherence of the data being collected with other statistical information. These processes might include questionnaire development, pilot studies, questionnaire testing, interviewer training,etc.
The accuracy of the data as well as its coherence may be influenced in many ways. For example:
by the sensitive nature of the information sought
if the words and concepts used do not have the same meaning for both respondents and survey takers
if concepts and wording are not harmonized with terms already in use, particularly for business surveys
