Applied network sampling

In principle, network sampling is an attractive method for estimating density and degree for large populations. This paper, based on the first extensive application of network sampling, reports some of the problems that may often arise in sampling and reaching respondents. The network sample or samples may be based on a list imperfectly reflecting the target population, the samples may be drawn nonrandomly from the list, and response may be nonrandom. We suggest and illustrate strategies for coping with each of these problems.