Sampling Concepts

Next to the decision for an adequate survey design the sample is crucial for the survey's quality. infas is well grounded in and has the required resources for drawing samples from different sources. Ultimate quality feature of infas samples is that each unit of the population has a calculable probability of being included in the sample. This means:

• no use of sample pools of respondents who have already shown their willingness to participate in surveys of any kind,
• no use of samples, which link the participation in a survey to the use of certain equipment,
• no use of purchasable addresses of commercial vendors.

infas is a member of the task force "Sampling" of the Arbeitskreis Deutscher Markt- und Sozialforschungsinstitute e.V. (ADM) (business association representing the interests of private-sector market and social research agencies in Germany) and consistently applies the quality standards for drawing samples of individuals, households as well as enterprises set by the ADM. infas regularly uses samples such as:

• telephone samples according to the ADM concept,
• samples based upon the data of registry offices,
• random walk samples according to the ADM concept,
• process data of labour and social administration,
• samples based upon membership files,
• samples of individuals from different populations,
• special samples i.e. cluster samples for classroom surveys (school and school grade samples, event samples).

Moreover, infas regularly carries out multiple-stage selection procedures and can, if required, edit business data for the purpose of sampling as well impact analysis (i.e. matching procedure).