Cut-off sampling and estimation

This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.

In cut-off sampling, part of the target population is deliberately excluded from selection. In business statistics, the frame and the sample are typically restricted to enterprises of at least a given size (e.g. a certain number of employees). The response burden is eliminated for the small enterprises, but assumptions must be used for the non-sampled part of the population. Cut-off sampling has merits but requires care when measuring size and methodological work with models.

This paper presents some empirical Swedish results based on one survey and administrative data. Different error sources and their effects on the overall accuracy are discussed.