Comparing two methods for estimating network size

In this paper we compare two methods for estimating the size of personal ne tworks 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 fa mily, coworkers). The results demonstrate a remarkable similarity between t he average network size generated by both methods (approximately 291). Simi lar results were obtained with a separate national sample. An attempt to co rroborate our estimates by replication among a population we suspect has la rge networks (clergy), yielded a larger average network size. Extensive inv estigation into the existence of response effects showed some preference fo r using certain numbers when making estimates, but nothing that would signi ficantly affect the estimate of network size beyond about 6 percent. We con clude that both methods for estimating personal network size yield valid an d reliable proxies for actual network size, but questions about accuracy re main.