General methodological approach of the NCS
The absence of a comprehensive list of congregations from which to draw a sample had been a major obstacle in survey research on congregations. The National Congregations Study (NCS) used a recent innovation in organizational sampling methodology to generate a high-quality, nationally representative sample of congregations. The key innovation is the insight that organizations attached to a random sample of individuals constitute a random sample of organizations. It therefore is possible to generate a representative sample of organizations even in the absence of a sampling frame that comprehensively lists the units in the organizational population. One simply starts with a representative sample of individuals and asks them to name the organization(s) to which they are attached. This procedure--called hyper-network sampling--has been used to sample other types of organizations; the NCS is the first study implementing it for congregations.
The 1998 and 2006 General Social Surveys included a set of items asking respondents who say they attend religious services at least once a year to report the name and location of their religious congregation. The GSS survey is an in-person interview with a representative sample of non-institutionalized adults in the United States. Until 2006, only English-speaking adults were included; beginning in 2006, the GSS is conducted in Spanish as well as in English. Congregations that are nominated in this randomly sampled way constitute the NCS national random sample.
The NCS then gathered data from these congregations using a one-hour interview with one key informant--a minister, priest, rabbi, or other staff person or leader--from each nominated congregation. These interviews were mainly conducted by telephone, but if telephone contact was difficult the interviews were conducted in person.
The NCS contributes to the sociological study of congregations by providing data that can be used to draw a nationally aggregate picture of congregations. NCS data can be used to address many questions, including but not limited to the following: What is the size distribution of the national congregational population? What is the nature of congregations' relations with denominations? What do worship services look like in American religion? To what extent do congregations engage in politics, social service delivery, and other community activities? In what ways do congregations with different social and organizational characteristics vary in their activities?
The NCS data requires weights to make its findings representative of all congregations in the country. Click here for a detailed description of those weights.
About the study