Comparing Two Methods for Estimating Network Size

In this paper we compare two methods for estimating the size of personal networks using a nationally representative sample of the United States. Both methods rely on the ability of respondents to estimate the number of people they know in specific subpopulations of the U.S. (e.g., diabetics, Native Americans) and people in particular relation categories (e.g., immediate family, coworkers). The results demonstrate a remarkable similarity between the average network size generated by both methods (approximately 291). Similar results were obtained with a separate national sample. An attempt to corroborate our estimates by replication among a population we suspect has large networks (clergy), yielded a larger average network size. Extensive investigation into the existence of response effects showed some preference for using certain numbers when making estimates, but nothing that would significantly affect the estimate of network size beyond about 6 percent. We conclude that both methods for estimating personal network size yield valid and reliable proxies for actual network size, but questions about accuracy remain.