How the Survey Was Conducted | 1995 Technical and Methodological Information
1999 Commercial Buildings Introduction The Commercial Buildings Energy Consumption Survey (CBECS) is conducted quadrennially by the Energy Information Administration (EIA) to provide basic statistical information about energy consumption and expenditures in U.S. commercial buildings and information about energy-related characteristics of these buildings. The survey is based upon a sample of commercial buildings selected according to the sample design requirements described below. A “building,” as opposed to an “establishment,” is the basic unit of analysis for the CBECS because the building is the energy-consuming unit. The 1999 CBECS was the seventh survey that had been conducted since 1979 The CBECS is conducted in two data-collection stages: a Building Characteristics Survey and an Energy Suppliers Survey. (For the 1999 CBECS, the Energy Suppliers Survey was initiated only if the respondents to the Building Characteristics Survey could not provide the energy consumption and expenditures information.) The Building Characteristics Survey collects information about selected commercial buildings through voluntary interviews with the buildings’ owners, managers, or tenants. In the 1999 survey, these data were collected using Computer-Assisted Telephone Interviewing (CATI) techniques. (In previous CBECS cycles, the information was collected during personal interviews.) During the Building Characteristics Survey, respondents are asked questions about the building size, how the building is used, types of energy-using equipment and conservation measures that are present in the building, the types of energy sources used, and for the 1999 survey, the amount and cost of energy used in the building. Building respondents could provide the consumption and expenditures information for approximately 60 percent of the sampled buildings. For the remaining 40 percent of buildings, the energy supplier names, addresses and account numbers were obtained. Upon completion of the Building Characteristics Survey, the Energy Suppliers Survey is initiated for those cases that did not provide consumption and expenditures information. This Suppliers Survey obtains data about the building’s actual consumption of and expenditures for energy from records maintained by energy suppliers. These billing data are collected in a mail survey conducted under EIA’s mandatory data collection authority. A survey research firm, under contract to EIA, conducts both the interviews for the Building Characteristics Survey and the mail survey for the Energy Suppliers Survey. 1999 CBECS This document describes the 1999 CBECS sample design, including the target population, the sample frames and sample selection rates, response rates, and the adjustment for unit nonresponse. Other information about survey procedures and methodology can be found in "Technical Information on CBECS" and "Background Information on CBECS".
Target Population The target population for the 1999 CBECS consisted of all commercial buildings in the United States (with the exception of commercial buildings located on manufacturing sites), that were constructed before 1995 and were larger than 1,000 square feet, and all commercial buildings constructed between 1995 and 1999 that were 10,000 square feet or more. To be eligible for the survey, a building had to satisfy three criteria: (1) it had to meet the size criteria described above; (2) it had to meet the survey’s definition of a building; and (3) it had to be used primarily for some commercial purpose. A building is defined by CBECS as a structure totally enclosed by walls that extend from the foundation to the roof that is intended for human access. To be used primarily for some commercial purpose, the building must have more than 50 percent of its floorspace devoted to activities that are neither residential, industrial, nor agricultural. The 1999 CBECS estimated that there were 4,657 thousand buildings in the target population.
There were two sample frames for the 1999 CBECS: a longitudinal sample frame consisting of buildings that were selected for the 1995 CBECS and a new construction sample frame consisting of buildings that were 10,000 square feet or greater and were constructed after April 1, 1995. Approximately 90 percent of the 1999 sample frame consisted of responding and nonresponding buildings that were eligible for and in-scope for the 1995 CBECS, plus buildings that were under construction at the time of the 1995 interview. The remaining 10 percent of the frame consisted of buildings from the F.W. Dodge List of New Construction. Information about the overall CBECS sample design is also available.
For the 1999 CBECS, the buildings in the sampling frame were stratified by their 1995 reported size class, by their use class and by their sampling frame source (area or list frame). The desired total sample size of 5,921 buildings was allocated proportionately to the strata. The buildings were subsampled within each stratum by a rate equal to the product of the uniform sampling rate (5,921/6,611) and the ratio of the target probability of selection for the stratum to the actual probability of selection of the building in the 1995 CBECS. This rate deviated from the uniform sampling rate because some buildings have been classified in one size or type stratum at the time they were originally listed and found to be in a different stratum at the time they were interviewed in 1995. Subsampling the buildings with such rates was expected to reduce the variance of the estimates by reducing the variation in the sampling weights. However, the benefit was somewhat limited given the high overall rate at which the 1995 CBECS buildings were retained for the 1999 survey.
The new construction sample frame obtained from the F.W. Dodge reports of new construction projects consisted of construction projects that were 10,000 square feet or larger, with a groundbreaking date between April 1, 1995 and June 1, 1999, and were located in the 129 CBECS PSUs. The new construction frame was intended to cover those buildings that were not part of the 1995 CBECS frame. The area frame for the 1995 CBECS was updated during the period of February through May of 1995. Two lists were obtained from F.W. Dodge: A large building list that included projects 250,000 square feet or larger; and a moderate-sized building list that included projects between 10,000 to 250,000 square feet. The large building list excluded buildings that were completed in 1995 if groundbreaking was prior to January 1, 1995, while the moderate-sized building list excluded buildings that were completed in 1995 if groundbreaking was prior to April 1, 1995. The large building list included all large projects while the moderate-sized building list included only a sample of projects. The F.W. Dodge lists included a range of project types, such as, new construction, building additions, and building renovations. For purposes of the 1999 CBECS, the definition of a “new” building was one that was completed after the cutoff date. In the event that the F.W. Dodge record referred to an addition, the building was treated as a “new” building only if (1) groundbreaking for the addition was after the cutoff date and (2) the addition more than doubled the size of the building. It was desirable to obtain 500 completed interviews from the new construction sample. With a targeted response rate of 75 percent, the new construction sample needed to contain 667 eligible buildings to yield 500 completed interviews. Based on the 1999 CBECS pilot experience, it was estimated that 1,080 new construction projects would yield about 667 eligible buildings. To ensure that the intended target would be met, a sample of 1,136 projects was selected with target sampling rates determined by project size classes. An optimization procedure established a set of desired relative sampling rates. Through an iterative process, sampling rates that yielded 1,136 projects were derived. A screener telephone interview was conducted with one or more of the project contacts that had been provided by F.W. Dodge. During the screening interview, information was obtained about the project that determined: (1) whether the project had been constructed; (2) the number of buildings included in the project; (3) whether the project was part of a larger facility and, if so, the purpose and ownership characteristics of that facility; and (4) a contact name for the CBECS interview. Then, for each individual building in the project information was obtained that determined: (1) the date the building was completed (or was expected to be completed); (2) whether an individual building project was a new building, an addition, or a renovation; and (3) the use and size of the building. Buildings with the following characteristics were determined to be ineligible for the new construction sample:
Of the 1,136 projects selected, 1,118 projects were determined to be eligible, 9 were determined to be ineligible, and the eligibility of the remaining 9 projects could not be determined. Among the 1,118 eligible projects, 3 projects were treated as a refusal. Of the 1,115 responding eligible projects, 31 were canceled. The remaining 1,084 projects contained 1,574 buildings. Of these 1,574 buildings, 515 buildings were determined to be out of scope and 1,059 were in scope. Finally, a sample of 683 buildings was selected among the 1,059 in-scope buildings. These 683 sampled buildings were located on 641 facilities. Table 1 shows the target building sampling rates for the new construction sample. Table 1. 1999 CBECS New Construction Sampling Rates by Size
1999 Projected Sampling Results The goal of the 1999 CBECS sampling procedures (both the longitudinal sample and the new construction list sample) was to achieve completed interviews for 5,000 buildings—4,500 buildings from the longitudinal sample and 500 buildings from the new construction sample.
In order to achieve the goal for number of respondents, a sample of 6,604 potential cases was selected, consisting of 5,921 buildings from the longitudinal sample frame and 683 buildings from the new construction sample frames. Of these 6,604 buildings, 6,313 buildings were found eligible for interviewing.
These procedures resulted in 5,430 completed interviews for a response rate of 86 percent. This total included 4,883 buildings from the longitudinal sample and 547 buildings from the new construction list sample.
An in-scope sample building, otherwise eligible for interview, for which no information is obtained, is called a unit nonresponse. The principal cause of the 14 percent unit nonresponse in the 1999 CBECS was the respondent’s refusal to participate in the interview. This was followed by the inability to contact and interview persons knowledgeable about the building, the inability to locate the sampled building by telephone or because the respondent did not speak English. Base weights assigned to the sample buildings were adjusted in an effort to reduce the nonsampling bias resulting from unit nonresponse. To represent these nonresponding buildings in the survey, the weights of respondent buildings were adjusted upwards within relatively homogeneous subclasses. The method used to make the weight adjustments for unit nonresponse had the effect of redistributing the weights of the nonrespondents to the responding eligible and ineligible buildings in the sample.
EIA does not receive or take possession of the names or addresses of individual respondents or any other individually identifiable energy data that could be specifically linked with an individual sample building or building respondent. All respondent names and addresses are maintained by the survey contractor for survey verification purposes only. Geographic identifiers and NOAA Weather Division identifiers are not included on micro-data files delivered to EIA. Geographic location information is provided to EIA at the Census division level. In addition, building characteristics that could potentially identify a particular responding building, such as number of floors, building square footage, and number of workers in the building, are masked to protect the respondent’s identity.
Contacts
http://www.eia.doe.gov/emeu/cbecs/1999sample.htm |