Home > Energy Users > Residential Home > 1997 Survey Methods

1997 Survey Methods

The Residential Energy Consumption Survey (RECS) was designed by the Energy Information Administration (EIA) to provide information about energy consumption within the residential sector. The RECS is conducted in two major parts: the Household Survey and the Energy Suppliers Survey. The Household Survey collects information about the housing unit through personal interviews with a representative national sample of households. The Rental-Agent Survey is an adjunct to the Household Survey and is used to verify information provided by renters in the Household Survey. In the Energy Suppliers Survey, data concerning actual energy consumption are obtained from household billing records maintained by the energy suppliers. The data are collected by questionnaires mailed to all the suppliers for the households in the Household Survey. This electronic report is based on the results of the Household Survey. A later report, Household Energy Consumption and Expenditures 1997, will present the results of the Energy Suppliers Survey. A subcontractor to EIA was used to collect and process the 1997 RECS. Click for copies of the data collection forms for the Household Survey and the adjunct Rental-Agent Survey.

This appendix contains detailed information about the sample design, Household Survey, its adjunct Rental Agent Survey, and confidentiality of the survey information.

Sample Design

The sample design for the 1997 RECS was based on the design used for the 1993 RECS. The universe for this sample design includes all housing units occupied as the primary residence in the 50 States and the District of Columbia. The RECS does not cover vacant housing units, seasonal units, nor second homes. Households on military installations are included. The definition of household is the same as that used by the U. S. Bureau of the Census. In RECS, by definition, the number of households is the same as the number of occupied primary housing units and these terms are used interchangeably. The universe was estimated to contain 101,481,000 households based on extrapolations from Current Population Survey (CPS) estimates at the time of the 1997 RECS (July 1997). This definition excludes group quarters such as military barracks, dormitories, and nursing homes, which are considered to be out-of-scope. It should be noted that the separation time between the estimates for 1993 and 1997 was 4 years, instead of the 2-2/3 years between the 1990 and 1993 estimates. Estimates of annual change need to take this difference into account.

The overall plan for the 1997 RECS included a basic sample of approximately 5,000 completed household interviews, plus a supplemental sample totaling approximately 800 completed interviews. The basic sample was designed to represent the total population of households in the United States, with specified levels of precision for each of the nine geographically defined Census divisions. The supplemental sample, included in the plan to meet special analytical needs, was designed to provide disproportionately large samples of households living below the poverty level, particularly those using electricity, fuel oil, or kerosene as the main space-heating fuel.

Multistage Area Probability Sample

In a multistage area probability sample design, the universe is broken up into successively smaller, statistically selected areas. The process starts with the selection of primary sampling units (PSUs) and ends with the selection of individual households.

Primary Sampling Units (PSUs)

PSUs are either metropolitan areas containing a central city of 50,000 or larger population, or they are counties or groups of counties containing small cities and rural areas. In the sample design used for the 1997 RECS, the total land area of the 50 States and the District of Columbia was divided into 1,786 PSUs. These PSUs were based on county and independent city boundaries and on Metropolitan Statistical Areas (MSAs) as defined in June 1990.

The primary mode of stratification of PSUs was by the nine Census divisions. Strata were separately defined within Census divisions for four populous States (California, Florida, New York, and Texas) and for two States with unique weather conditions (Alaska and Hawaii). Stratification was also based on MSA or nonMSA status of PSUs and, to the extent feasible, on dominant residential space-heating fuel and weather conditions. PSUs were grouped into 116 strata with one PSU selected from each strata. The PSUs that were selected for the 1993 RECS were also used for the 1997 RECS.

Secondary Sampling Units (SSUs)

A number of SSUs, usually eight or more, were selected in each PSU. SSUs consisted of one or more Census blocks, selected directly from Census statistics. Blocks were combined, as necessary, to create SSUs that contained at least 50 housing units.

The 1997 RECS sample design completed the redesign effort that started with the 1993 RECS. The SSUs used for the 1997 RECS were either the SSUs selected in the redesign effort or were SSUs selected as part of a new construction update procedure.

The starting point for the SSU new construction update procedure was the set of SSUs selected for the 1993 RECS. The first step was to expand the 1993 SSUs. A new construction update procedure was used to determine if significant new construction--defined as groups of 50 or more housing units--had occurred within the expanded SSUs since 1993. This was based on a canvass, primarily by telephone, of local sources of information, such as building-permit-issuing agencies, zoning boards, and tax offices. If no significant new construction had occurred, the SSU selected for the 1993 RECS was used for the 1997 RECS. If significant new construction had occurred, rough counts of the number of housing units by block were obtained for the expanded SSU, the expanded SSU was divided into segments, and a segment was selected. The selected segment was then used as the SSU for the 1997 RECS.

The detailed field listings of all housing units in the 1997 RECS SSUs were either carried over from the 1993 RECS or were created by field workers who visited the SSUs and identified each housing unit by street address, apartment number, or other obvious features. New field listings were necessary for SSUs in PSUs where the redesign effort was not completed for the 1993 RECS and for SSUs where significant new construction was found in the corresponding expanded SSU. A penultimate cluster of approximately 50 housing units was selected from each SSU.

Addresses of these housing units were placed in a database used for actual sample selection.

Sample Selection--Ultimate Clusters

Specific addresses chosen from each of the field listings comprised the ultimate clusters of the 1997 RECS sample. An ultimate cluster of housing units to be contacted for interview (averaging 5.6 housing units for the 1997 RECS) was randomly selected by computer from the penultimate cluster; these housing units constituted the assignments given to interviewers.

Population of Special Interest

The 1997 survey featured a supplemental sample of low-income households designed to be merged with the main RECS sample and to meet special analytical needs of the Office of Family Assistance, Family Support Administration (FSA), U.S. Department of Health and Human Services. The FSA is interested in households living below the poverty level.

Procedures for over-sampling this population were based on interviewer observations during the field listing of SSUs. Interviewers were instructed to rate the general income level of each block in the listing segment based on their observations and their general knowledge of the area. Interviewers placed each listing segment into one of four groups: Wealthy (highest 25 percent); Upper-Middle Class (second quartile); Lower-Middle Class (third quartile); or Poor or Near Poor (lowest 25 percent). Whenever possible, interviewers also recorded main heating fuel for each listing segment. Households in the Lower-Middle Class and Poor or Near Poor categories were sampled at a higher rate.

It is not possible to divide the sample into the main sample and supplemental sample, but it is possible to estimate how many observations of various types were added as a result of the supplemental low-income sample.

An estimated 808 interviews were completed in the households selected as part of the low-income supplement. Some 31.8 percent of completed interviews in the supplemental sample were with households living below the poverty level, compared with 14.5 percent of completed interviews in the main sample. The number of households below the Low-Income Home Energy Assistance Program (LIHEAP) level were 57.3 percent of the supplemental sample and 34.1 percent of the main sample.

Household Survey

A complete RECS interview consists of data for a completed household questionnaire and a signed Authorization Form. The large majority of interviews were completed via a Computer Assisted Personal Interviewing (CAPI) system. The survey instrument was programmed by EIA personnel using the BLAISE software system. The paper version of the survey instrument can be found in Form EIA-457A, "Household Questionnaire." Because of early technical problems, some of the initial interviews had to be completed using the paper version of the questionnaire. At the end of each interview, the household respondent was asked to sign an Authorization Form. The signed Authorization Form gave permission for EIA's subcontractor to obtain the housing unit's energy bills from each supplier of energy.

A total of 8,310 housing units were selected to participate in the 1997 RECS. Of these 8,310 households, 7,285 were determined to be eligible to participate. Completed interviews were obtained for 5,902 (81.0 percent) of these eligible households. This section describes the procedures involved in collecting the completed interviews.

Conducting the Interviews

Interviewer Training

In April 1997, two separate three-day training sessions were held in Washington, DC. These sessions were attended by approximately 220 interviewers. Each session was led by a group of trainers who had attended a four-day trainers' workshop in Rockville, MD. All training sessions were monitored by Department of Energy staff.

The Interviewers

A total of 214 interviewers completed one or more personal interviews for this study. Seventy-five interviewers (35 percent) had completed interviews during a prior RECS. The remainder were conducting their first RECS but had prior interviewing experience, either with other survey research organizations or with the U.S. Bureau of the Census.

Interviewers conducted an average of 27 interviews. Four interviewers completed fewer than seven interviews each, with an average of three per interviewer. Fifteen interviewers completed 50 or more interviews each, with an average of 58 per interviewer. Twenty percent of the personal interviews were verified by telephone or mail to ensure that interviews were conducted as intended.

The Interview

Household interviews were conducted with the householder or the householder's spouse and, on average, lasted 29 minutes; nearly 80 percent of the interviews lasted between 15 and 45 minutes. The questions covered energy-related features of the household, such as the type of heating and cooling systems, the fuels used for heating and cooling, household appliances and their usage, the receipt of government assistance for the cost of heating, and demographic data on household members.

Data Collection Dates

Approximately three-quarters of the personal interviews were completed between the middle of April and the middle of June 1997. Ninety-nine percent of the entire sample was completed by mid-August. In a few sample locations with low response rates, interviewing continued through August. In late August, an abbreviated, self-administered version of the household questionnaire was mailed to 1,421 sample households who still had not completed a personal interview. A total of 181 usable mail questionnaires were returned by the end of September 1997. A mail questionnaire was considered usable if the respondent had completed the majority of the questionnaire and the Authorization Form was signed. A follow-up contact was made with all respondents who completed a personal interview and reported paying for at least one fuel but did not complete an authorization form. Attempts were made to secure signed authorization forms from approximately 570 respondents. This follow-up continued through January 1998 and resulted in an additional 95 signed authorization forms.

Data Collection Procedures

In an effort to minimize nonresponse and, therefore, maximize the validity of the survey data, a multiwave, multicontact approach was employed. Before the initial personal contacts, a letter stressing the purpose and importance of the survey was sent to each household with a street address. Beginning in April 1997, interviewers made several callbacks at different times of the day, throughout the week, in an effort to minimize the number of uncontacted households. The interviewers also queried neighbors regarding the most opportune times to contact the prospective respondent.

After initial attempts to complete interviews at the selected housing units were exhausted, field supervisors determined which cases would be reassigned to another interviewer. Types of noninterview households that were reassigned included cases where the householder refused to participate and cases where the householder was not available or not at home. Types of noninterview households that were not reassigned included cases where the householder would be unable to complete an interview during the field period due to absence or illness and cases where the household had moved after the initial contact. Reassignments continued throughout the field period.

Mail follow-up attempts were made at households that had not completed a personal interview. An abbreviated, self-administered version of the questionnaire was mailed to these households with a letter asking that they return the completed questionnaire in the business reply envelope provided. The mailing also included a copy of the Authorization Form for the respondents to fill out and sign. A pen was included with the mailing as an incentive.

After all data collection attempts (both personal interview and the mailed questionnaire), 1,383 households or 19.0 percent of all eligible housing units had not responded.

Table A1 provides a summary of the data collection activities.

Various response and nonresponse rates were compared across Census region, urban status, and housing structure type. Personal interviewers were most successful in the South (81.1 percent) and the Midwest (80.2 percent), in rural areas (85.0 percent), and in single-family and mobile homes (80.5 percent). Conversely, the interviewers had their lowest success rates in the Northeast (73.1 percent), in urban and suburban areas (76.4 percent combined), and in buildings with five or more residential units (72.1 percent). However, when comparing these groups, it is important to remember that their characteristics are not necessarily independent. For example, apartment buildings are concentrated in urban areas.

The total response-rate patterns generally were not affected by including the mailed-questionnaire responses. However, response rates for the mail efforts tended to be higher where the refusal rate to the personal interview was higher.

Data Editing

Data for completed interviews were transferred to the main server at the survey contractor's headquarters via modem. The data were then sent to the survey subcontractor's headquarters for further processing. All paperwork was mailed to the survey subcontractor's headquarters. The paperwork, including the Housing Unit Record Sheet (HURS), the Authorization Form, and the Housing Unit Address Lists were reviewed to ensure that all forms had been completed correctly and that the correct housing unit had been interviewed.

Edits were programmed into the Household Questionnaire and this resulted in far fewer missing data items than in previous surveys. See Appendix B, "Survey Estimates and Data Quality," for more information on this topic.

The subcontractor attempted to resolve inconsistencies or ambiguities in the data by referencing interviewer notes and other parts of the questionnaire. When these efforts failed to resolve important problems, particularly those involving heating fuels or heating equipment and/or relationships between questionnaire responses, the subcontractor made a follow-up telephone contact with the rental agent or with a member of the household in question.

Rental-Agent Survey

The Rental-Agent Survey is an adjunct to the Household Survey and is used to verify information furnished by certain RECS households on fuels used, main heating equipment, how fuels are paid for, and other energy-related topics. Telephone interviews were conducted using Form EIA-457C, "Rental Agents, Landlords, and Apartment Managers Telephone Survey," with the rental agents and landlords of the following types of RECS households: households that did not pay for their fuels, households who paid a third party for their fuel and who rent their living quarters or own and occupy living quarters in a multiunit building.

The interviews with rentals agents or their representatives were conducted in early fall 1997. Altogether, 186 landlords or rental agents were interviewed; these interviews covered 382 households. These 382 households represented 59 percent of the 650 total households who were eligible for inclusion in the Rental Agent Survey.

Comparisons were made between rental agents' and household respondents' reports on their building's year of construction; main space-heating and water-heating fuels; main space-heating equipment; fuel for cooking range; central air-conditioning information; and how the fuels for all of these uses are paid for. Each discrepancy was examined and changes were made to the household data whenever it was judged that the rental agent was more knowledgeable than the household respondent on the different items of information.

Generally, the person who paid for a specific fuel for a specific use was deemed the more knowledgeable person. However, error resolutions were made only after careful examination and consideration of all available sources of information including the rental-agent questionnaire, the household questionnaire, and questionnaires of other households located in the same building. Landlords and rental agents were usually judged more knowledgeable about the year the building was built and the type of main heating equipment; household respondents were typically deemed more reliable sources concerning central air-conditioning and fuel for cooking range.

Confidentiality of Information

EIA does not receive nor take possession of the names or addresses of individual respondents or any other individually identifiable energy data that could be specifically linked with a household respondent; the data are collected for statistical purposes only. All names and addresses and identifiable information are maintained by the survey subcontractor for verification purposes only. The household records that are placed on the public-use data file do not have name or address information. Additional measures have been taken to mask the data for further confidentiality protection. Unlike other EIA surveys, the consumption surveys pledge confidentiality to their respondents.

Return to Contents Page