National Survey of Religious Identification, 1990

Data Archive > U.S. Surveys > General Population > National > Other > Summary


The National Survey of Religious Identification relates to a random digit-dialed telephone survey of 113,000 American households in the continental U.S. (48 states). The data was collected over a 13-month period by ICR Survey Research Group of Media, PA as part of their omnibus market research (EXCEL) survey. The prime question on the file is: What is your religion? If the initial answer was Protestant, there was a further question as to which denomination. The respondent is a randomly chosen (last birthday) adult over 18 years. Nineteen other socio-demographic questions are attached to this. The NSRI makes a significant contribution by presenting a large sample size reflecting the true richness of the country's religious tapestry and the national coverage necessary to provide high quality statistics on what is actually happening around us.

Data File
Cases: 113,723
Variables: 32
Weight Variable: POPWGHT, HHWGHT
Data Collection
Date Collected: April 1989 - April 1990
Original Survey (Instrument)
The National Survey of Religious Identification 1989-90
Collection Procedures
The data were collected over a 13-month period, April 1989 - April 1990 at the rate of 2,000 interviews a week by ICR Survey Research Group of Media, PA as part of their omnibus market research (EXCEL) survey. In effect, this involved purchasing time for a question to be included in the survey alongside a variety of other constantly changing questions on topics as varied as cable TV use, preference for consumer items, and social or political issues. The question of religious identity was included in 113 rounds. Inclusion on a multipurpose questionnaire was assumed to provide better results than if the general public was called and asked to participate in a purely religious survey. The question of religious identity in the multipurpose context often appear appropriate when it was positioned alongside others on lifestyle, attitudes, food preferences or public policy issues. As a result, once a respondent agreed to be interviewed, the actual item refusal rate to our religious question was a very low 2.3 percent.
Sampling Procedures
This survey used the ICR's Computer-Assisted Telephone Interviewing (CATI) system. The computer randomly chose telephone numbers across the United States in proportion to the number of residential telephone lines. This technique, known as Random Digit Dialing (RDD), creates a geographically representative sample. We used the GENYSYS system to create 113 individual national samples. Basically, GENYSYS chooses an area code, then a telephone exchange, and then the first two digits of a four-digit suffix. Then the computer randomly dials the last two numbers. In this manner a sample frame with very fine geographical stratification is created. The respondent within the household was a randomly chosen adult picked according to who had the last birthday.
Principal Investigators
Barry A. Kosmin
Notes on Weighted Data
The data which are weighted by ICR using the latest Census Burean statistics, reflect the known composition of U.S. households and the total population. The weighting, which is incorporated into each record, takes into account the disproportionate probabilities of household projection due to the number of separate telephone lines and the probability associated with the random selection of an individual household member. Following application of the above weights, the sample is post-stratified and balanced by key demographics, such as age, sex, region and education. However, weighting cannot compensate for characteristics that are neither geographic nor demographic in nature. The most obvious is an inability to communicate in English or Spanish, the interview languages. This means there may be a tendency to underestimate some of the smaller religious groups that contain a high proportion of recent immigrants. Nevertheless, the range of error will not be enormous even in these cases. The overall sampling error for the survey is 0.4 percent at the 95 percent confidence level.

Bookmark and Share