Using an access panel as a sampling frame for voluntary household surveys.

Abstract

Voluntary household surveys are currently faced with a number of serious challenges. These challenges include the increasing reluctance to participate in surveys, the necessity to use probability sampling as a standard practice, and the steadily growing demand for statistical information. It is argued that new approaches of survey design have to be developed in order to cope with this problem. Establishing an access panel of households ready to respond in surveys constitutes one possible solution: According to the access panel concept, households having participated in surveys based on highly reliable random samples of official statistics (like the German microcensus) should be recruited for regular participation in voluntary surveys of official statistics. These households "ready to respond" are included in the access panel, which then would be available as a sampling frame for random samples. The general readiness of these households to co-operate with official statistics would permit to achieve relatively high response rates. At the same time, it would be possible to react more flexibly than in the past to new data demand. This contribution outlines the concept of an access panel in official statistics and summarises the most important results of a large-scale pilot study carried out in the German statistical system from late 2000 to 2003.