Detailed Methodology

The Belden Russonello & Stewart survey of national adults, conducted for Smart Growth America and the National Association of Realtors®, interviewed 1,130 American adults ages 18 and older. The interviews took place from August 26 to September 6, 2004, using the Knowledge Networks web-enabled panel.

The Knowledge Networks sample is derived from a random digit dial (RDD) telephone methodology that represents all U.S. households with telephones. The company employs a complex sample stratification design that incorporates the known probabilities of selection associated with geographical location, the number of phone lines, and whether or not the phone number is listed. Persons in selected households are invited by telephone to participate in the web-enabled panel. Those who agree to participate are sent an internet appliance and receive an internet service connection provided by Knowledge Networks. In some cases, people who already have computers and internet service are permitted to participate using their own equipment. These panelists receive unique log-in information for accessing surveys online.

The margin of sampling error for the entire sample is plus or minus three percentage points at the 95 percent level of confidence. The margin of error is larger for subgroups of the population.

The demographic characteristics of the sample obtained through these selection methods were matched to U.S. Census data from 2000. The data collected were weighted statistically to bring age and race into their proper proportions for American adults ages eighteen and older. The table below shows the demographic composition of the survey sample.

The following are the regional breaks used in the study:

Composition Table of Survey Respondents